{"meta": {"count": 2000, "db_response_time_ms": 40, "page": 1, "per_page": 100, "groups_count": null, "x_query": {"oql": "get works where retracted is (false)\n  and year is (2025)\n  and title-abstract has ((stemmed \"language model\" OR stemmed \"large language model\" OR stemmed \"vision language model\") AND (stemmed \"multimodal alignment\" OR stemmed \"pre training\" OR stemmed \"pretraining\" OR stemmed \"scaling law\"))\n  and type is (article or preprint or review);\nthen sample (2000) of those works with seed (42)", "oqo": {"get_rows": "works", "filter_rows": [{"column_id": "is_retracted", "value": false}, {"column_id": "publication_year", "value": 2025}, {"join": "or", "filters": [{"column_id": "title_and_abstract.search", "value": "\"language model\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"large language model\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"vision language model\"", "operator": "has"}]}, {"join": "or", "filters": [{"column_id": "title_and_abstract.search", "value": "\"multimodal alignment\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"pre training\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"pretraining\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"scaling law\"", "operator": "has"}]}, {"join": "or", "filters": [{"column_id": "type", "value": "article"}, {"column_id": "type", "value": "preprint"}, {"column_id": "type", "value": "review"}]}], "sample": 2000, "seed": "42"}, "url": "/works?filter=is_retracted:false,publication_year:2025,title_and_abstract.search:%22language model%22|%22large language model%22|%22vision language model%22,title_and_abstract.search:%22multimodal alignment%22|%22pre training%22|%22pretraining%22|%22scaling law%22,type:article|preprint|review&sample=2000&seed=42&per_page=100&page=1"}, "cost_usd": 0.001}, "results": [{"id": "https://openalex.org/W4414613812", "doi": "https://doi.org/10.1101/2025.09.25.678635", "title": "Edit Distance Embedding with Genomic Large Language Model", "publication_year": 2025, "publication_date": "2025-09-29", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100394772", "display_name": "Xiang Li", "orcid": "https://orcid.org/0000-0002-4962-002X", "observed_orcids": ["https://orcid.org/0000-0002-4962-002X"]}, "institutions": [{"id": "https://openalex.org/I130769515", "display_name": "Pennsylvania State University", "ror": "https://ror.org/04p491231", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130769515"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xiang Li", "raw_affiliation_strings": ["Department of Computer Science and Engineering, The Pennsylvania State University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering, The Pennsylvania State University", "institution_ids": ["https://openalex.org/I130769515"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100451971", "display_name": "Ke Chen", "orcid": "https://orcid.org/0000-0001-5470-6621", "observed_orcids": ["https://orcid.org/0000-0001-5470-6621"]}, "institutions": [{"id": "https://openalex.org/I130769515", "display_name": "Pennsylvania State University", "ror": "https://ror.org/04p491231", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130769515"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ke Chen", "raw_affiliation_strings": ["Department of Computer Science and Engineering, The Pennsylvania State University"], "raw_orcid": "https://orcid.org/0000-0001-5470-6621", "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering, The Pennsylvania State University", "institution_ids": ["https://openalex.org/I130769515"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5072479291", "display_name": "Yi-Jia Zhang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I76214153", "display_name": "Lanzhou University", "ror": "https://ror.org/01mkqqe32", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I76214153"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yijia Zhang", "raw_affiliation_strings": ["School of Information Science and Engineering, Lanzhou University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Information Science and Engineering, Lanzhou University", "institution_ids": ["https://openalex.org/I76214153"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5052979637", "display_name": "Mingfu Shao", "orcid": "https://orcid.org/0000-0001-6112-5139", "observed_orcids": ["https://orcid.org/0000-0001-6112-5139"]}, "institutions": [{"id": "https://openalex.org/I130769515", "display_name": "Pennsylvania State University", "ror": "https://ror.org/04p491231", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130769515"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Mingfu Shao", "raw_affiliation_strings": ["Department of Computer Science and Engineering, The Pennsylvania State University", "Huck Institutes of the Life Science, The Pennsylvania State University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering, The Pennsylvania State University", "institution_ids": ["https://openalex.org/I130769515"]}, {"raw_affiliation_string": "Huck Institutes of the Life Science, The Pennsylvania State University", "institution_ids": ["https://openalex.org/I130769515"]}]}], "abstract_inverted_index": {"Edit": [0], "distance": [1, 35, 41, 50], "is": [2, 12, 74, 141], "a": [3, 28, 77, 129, 148, 182], "fundamental": [4], "metric": [5], "in": [6, 42, 59, 101, 109, 170, 181], "genomic": [7, 102, 150], "sequence": [8, 22, 111, 134, 186], "analysis,": [9], "yet": [10], "it": [11], "computationally": [13], "expensive": [14], "to": [15, 132], "calculate.": [16], "A": [17], "practical": [18], "approach": [19], "for": [20, 97], "large-scale": [21], "analysis": [23, 112], "involves": [24], "mapping": [25, 73], "sequences": [26], "into": [27], "normed": [29], "space": [30], "and": [31, 58, 166], "approximating": [32, 136, 171], "the": [33, 37, 72, 87, 137, 172], "edit": [34, 49, 138, 173], "using": [36, 122], "more": [38], "efficiently": [39], "computed": [40], "that": [43, 160], "space.": [44], "This": [45], "process,": [46], "known": [47], "as": [48, 76], "embedding,": [51], "has": [52], "been": [53], "extensively": [54], "studied": [55], "both": [56], "theoretically": [57], "practice.": [60], "Recently,": [61], "embedding": [62, 168], "methods": [63, 91, 169], "based": [64, 146], "on": [65, 147], "machine": [66, 164], "learning": [67, 145, 165], "have": [68, 105], "gained": [69], "popularity,": [70], "where": [71], "represented": [75], "neural": [78], "network": [79], "whose": [80], "parameters": [81], "are": [82], "learned": [83], "from": [84], "data.": [85], "However,": [86], "accuracy": [88, 180], "of": [89], "these": [90], "remains": [92], "unsatisfactory,": [93], "leaving": [94], "much": [95], "room": [96], "improvement.": [98], "Recent": [99], "advancements": [100], "language": [103, 124, 152], "models": [104], "shown": [106], "remarkable": [107], "performance": [108], "various": [110], "applications.": [113], "We": [114, 126], "investigate": [115], "if": [116], "improved": [117, 179], "embeddings": [118, 135], "can": [119], "be": [120], "achieved": [121, 177], "DNA": [123], "models.": [125], "introduce": [127], "LLMED,": [128], "model": [130], "designed": [131], "produce": [133], "distance.": [139], "LLMED": [140, 161, 175], "trained": [142], "via": [143], "contrastive": [144], "pretrained": [149], "large": [151], "model.": [153], "Through": [154], "extensive": [155], "experimental": [156], "comparisons,": [157], "we": [158], "show": [159], "surpasses": [162], "leading": [163], "rule-based": [167], "distance;": [174], "also": [176], "significantly": [178], "critical": [183], "application,": [184], "similar": [185], "search.": [187]}, "primary_topic": {"id": "https://openalex.org/T12946", "display_name": "Fractal and DNA sequence analysis", "score": 0.46480000019073486, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12946", "display_name": "Fractal and DNA sequence analysis", "score": 0.46480000019073486, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10015", "display_name": "Genomics and Phylogenetic Studies", "score": 0.22550000250339508, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T11269", "display_name": "Algorithms and Data Compression", "score": 0.20749999582767487, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1101/2025.09.25.678635", "is_oa": true, "landing_page_url": "https://doi.org/10.1101/2025.09.25.678635", "pdf_url": "https://www.biorxiv.org/content/biorxiv/early/2025/09/29/2025.09.25.678635.full.pdf", "source": {"id": "https://openalex.org/S4306402567", "display_name": "bioRxiv (Cold Spring Harbor Laboratory)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I2750212522", "host_organization_name": "Cold Spring Harbor Laboratory", "host_organization_lineage": ["https://openalex.org/I2750212522"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": "bioRxiv", "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406863965", "doi": "https://doi.org/10.1016/j.ipm.2025.104072", "title": "KRongBERT: Enhanced factorization-based morphological approach for the Korean pretrained language model", "publication_year": 2025, "publication_date": "2025-01-27", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102639173", "display_name": "Hyunwook Yu", "orcid": "https://orcid.org/0009-0000-4723-0135", "observed_orcids": ["https://orcid.org/0009-0000-4723-0135"]}, "institutions": [{"id": "https://openalex.org/I67900169", "display_name": "Chung-Ang University", "ror": "https://ror.org/01r024a98", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I67900169"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Hyunwook Yu", "raw_affiliation_strings": ["Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea", "institution_ids": ["https://openalex.org/I67900169"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111226626", "display_name": "Yejin Cho", "orcid": "https://orcid.org/0009-0002-0333-6506", "observed_orcids": ["https://orcid.org/0009-0002-0333-6506"]}, "institutions": [{"id": "https://openalex.org/I1174212", "display_name": "University of Southern California", "ror": "https://ror.org/03taz7m60", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1174212"]}, {"id": "https://openalex.org/I67900169", "display_name": "Chung-Ang University", "ror": "https://ror.org/01r024a98", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I67900169"]}], "countries": ["KR", "US"], "is_corresponding": false, "raw_author_name": "Yejin Cho", "raw_affiliation_strings": ["Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea", "University of Southern California, 3551 Trousdale Pkwy, Los Angeles, 90089, CA, United States"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea", "institution_ids": ["https://openalex.org/I67900169"]}, {"raw_affiliation_string": "University of Southern California, 3551 Trousdale Pkwy, Los Angeles, 90089, CA, United States", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5086973876", "display_name": "Geunchul Park", "orcid": "https://orcid.org/0000-0001-8388-9471", "observed_orcids": ["https://orcid.org/0000-0001-8388-9471"]}, "institutions": [{"id": "https://openalex.org/I878022262", "display_name": "Korea Institute of Science & Technology Information", "ror": "https://ror.org/01k4yrm29", "country_code": "KR", "type": "facility", "lineage": ["https://openalex.org/I2801339556", "https://openalex.org/I4210144908", "https://openalex.org/I4387152098", "https://openalex.org/I878022262"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Geunchul Park", "raw_affiliation_strings": ["Division of Supercomputing, Korea Institute of Science and Technology Information, 245 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Division of Supercomputing, Korea Institute of Science and Technology Information, 245 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea", "institution_ids": ["https://openalex.org/I878022262"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5000615413", "display_name": "Mucheol Kim", "orcid": "https://orcid.org/0000-0003-2682-2195", "observed_orcids": ["https://orcid.org/0000-0003-2682-2195"]}, "institutions": [{"id": "https://openalex.org/I67900169", "display_name": "Chung-Ang University", "ror": "https://ror.org/01r024a98", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I67900169"]}], "countries": ["KR"], "is_corresponding": true, "raw_author_name": "Mucheol Kim", "raw_affiliation_strings": ["Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea"], "raw_orcid": "https://orcid.org/0000-0003-2682-2195", "affiliations": [{"raw_affiliation_string": "Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea", "institution_ids": ["https://openalex.org/I67900169"]}]}], "abstract_inverted_index": {"The": [0, 142], "bidirectional": [1], "encoder": [2], "representations": [3], "from": [4], "transformers": [5], "(BERT)": [6], "model": [7, 44, 81], "has": [8], "achieved": [9], "remarkable": [10], "success": [11], "in": [12, 70, 88], "various": [13], "natural": [14, 92], "language": [15, 24, 43, 93], "processing": [16], "tasks": [17, 95], "for": [18], "Latin-based": [19], "languages.": [20], "However,": [21], "the": [22, 54, 62, 98, 119, 132, 135], "Korean": [23, 71, 111, 136], "presents": [25], "unique": [26, 55], "challenges": [27], "with": [28, 67], "limited": [29], "data": [30, 120], "resources": [31], "and": [32, 72], "complex": [33], "linguistic": [34, 56], "structures.": [35], "In": [36], "this": [37], "paper,": [38], "we": [39], "present": [40], "KRongBERT,": [41], "a": [42, 48], "specifically": [45], "designed": [46], "through": [47], "morphological": [49], "approach": [50], "to": [51, 77, 84, 97, 108], "effectively": [52], "address": [53], "complexities": [57, 133], "of": [58, 118, 134], "Korean.": [59], "KRongBERT": [60, 103, 129], "mitigates": [61], "out-of-vocabulary": [63], "issues": [64], "that": [65, 128], "arise": [66], "byte-pair-encoding": [68], "tokenizers": [69], "incorporates": [73], "language-specific": [74], "embedding": [75], "layers": [76], "enhance": [78], "understanding.": [79], "Our": [80, 125], "demonstrates": [82], "up": [83], "an": [85], "1.56%": [86], "improvement": [87], "performance": [89, 106], "on": [90], "specific": [91], "understanding": [94], "compared": [96, 107], "traditional": [99], "BERT": [100, 112], "implementations.": [101], "Notably,": [102], "achieves": [104], "superior": [105], "existing": [109], "state-of-the-art": [110, 140], "models": [113], "while": [114], "utilizing": [115], "only": [116], "11.42%": [117], "required": [121], "by": [122], "other": [123], "models.": [124], "experiments": [126], "demonstrate": [127], "efficiently": [130], "handles": [131], "language,": [137], "outperforming": [138], "current": [139], "approaches.": [141], "code": [143], "is": [144], "publicly": [145], "available": [146], "at": [147], "https://github.com/Splo2t/KRongBERT": [148], ".": [149]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.036400001496076584, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.0005000000237487257, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.ipm.2025.104072", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.ipm.2025.104072", "pdf_url": null, "source": {"id": "https://openalex.org/S174847851", "display_name": "Information Processing & Management", "issn_l": "0020-0271", "issn": ["0020-0271", "0306-4573", "1873-5371", "1878-4089"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-3", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Information Processing &amp; Management", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411968027", "doi": "https://doi.org/10.1016/j.neucom.2025.130617", "title": "In the eyes of a language model: A comprehensive examination through eye-tracking data", "publication_year": 2025, "publication_date": "2025-07-02", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5059707020", "display_name": "Luca Dini", "orcid": "https://orcid.org/0009-0004-2070-7238", "observed_orcids": ["https://orcid.org/0009-0004-2070-7238"]}, "institutions": [{"id": "https://openalex.org/I108290504", "display_name": "University of Pisa", "ror": "https://ror.org/03ad39j10", "country_code": "IT", "type": "education", "lineage": ["https://openalex.org/I108290504"]}, {"id": "https://openalex.org/I4210124522", "display_name": "Institute for Computational Linguistics \u201cA. Zampolli\u201d", "ror": "https://ror.org/028g3pe33", "country_code": "IT", "type": "facility", "lineage": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}, {"id": "https://openalex.org/I4210155236", "display_name": "National Research Council", "ror": "https://ror.org/04zaypm56", "country_code": "IT", "type": "nonprofit", "lineage": ["https://openalex.org/I4210155236"]}], "countries": ["IT"], "is_corresponding": false, "raw_author_name": "Luca Dini", "raw_affiliation_strings": ["Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy", "University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, 56127, Italy"], "raw_orcid": "https://orcid.org/0009-0004-2070-7238", "affiliations": [{"raw_affiliation_string": "Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy", "institution_ids": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}, {"raw_affiliation_string": "University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, 56127, Italy", "institution_ids": ["https://openalex.org/I108290504"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114231065", "display_name": "Luca Moroni", "orcid": "https://orcid.org/0009-0006-1210-5098", "observed_orcids": ["https://orcid.org/0009-0006-1210-5098"]}, "institutions": [{"id": "https://openalex.org/I861853513", "display_name": "Sapienza University of Rome", "ror": "https://ror.org/02be6w209", "country_code": "IT", "type": "education", "lineage": ["https://openalex.org/I861853513"]}], "countries": ["IT"], "is_corresponding": false, "raw_author_name": "Luca Moroni", "raw_affiliation_strings": ["Sapienza University of Rome/Sapienza NLP group, Via Ariosto, 25, Roma, 00185, Italy"], "raw_orcid": "https://orcid.org/0009-0006-1210-5098", "affiliations": [{"raw_affiliation_string": "Sapienza University of Rome/Sapienza NLP group, Via Ariosto, 25, Roma, 00185, Italy", "institution_ids": ["https://openalex.org/I861853513"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5057659257", "display_name": "Dominique Brunato\u22c4", "orcid": "https://orcid.org/0000-0003-3256-4794", "observed_orcids": ["https://orcid.org/0000-0003-3256-4794"]}, "institutions": [{"id": "https://openalex.org/I4210124522", "display_name": "Institute for Computational Linguistics \u201cA. Zampolli\u201d", "ror": "https://ror.org/028g3pe33", "country_code": "IT", "type": "facility", "lineage": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}, {"id": "https://openalex.org/I4210155236", "display_name": "National Research Council", "ror": "https://ror.org/04zaypm56", "country_code": "IT", "type": "nonprofit", "lineage": ["https://openalex.org/I4210155236"]}], "countries": ["IT"], "is_corresponding": true, "raw_author_name": "Dominique Brunato", "raw_affiliation_strings": ["Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"], "raw_orcid": "https://orcid.org/0000-0003-3256-4794", "affiliations": [{"raw_affiliation_string": "Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy", "institution_ids": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5084812833", "display_name": "Felice Dell\u2019Orletta\u22c4", "orcid": "https://orcid.org/0000-0003-3454-9387", "observed_orcids": ["https://orcid.org/0000-0003-3454-9387"]}, "institutions": [{"id": "https://openalex.org/I4210124522", "display_name": "Institute for Computational Linguistics \u201cA. Zampolli\u201d", "ror": "https://ror.org/028g3pe33", "country_code": "IT", "type": "facility", "lineage": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}, {"id": "https://openalex.org/I4210155236", "display_name": "National Research Council", "ror": "https://ror.org/04zaypm56", "country_code": "IT", "type": "nonprofit", "lineage": ["https://openalex.org/I4210155236"]}], "countries": ["IT"], "is_corresponding": false, "raw_author_name": "Felice Dell\u2019Orletta", "raw_affiliation_strings": ["Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy"], "raw_orcid": "https://orcid.org/0000-0003-3454-9387", "affiliations": [{"raw_affiliation_string": "Institute of Computational Linguistics \u201cAntonio Zampolli\u201d (CNR_ILC)/ItaliaNLP Lab, Via Giuseppe Moruzzi, 1, Pisa, 56124, Italy", "institution_ids": ["https://openalex.org/I4210124522", "https://openalex.org/I4210155236"]}]}], "abstract_inverted_index": {"Cognitive": [0], "signals,": [1], "particularly": [2], "eye-tracking": [3, 96, 112], "data,": [4], "offer": [5], "a": [6, 31, 58, 79, 119], "unique": [7], "lens": [8], "for": [9, 175], "understanding": [10], "human": [11, 48, 102, 158, 169, 201, 218], "sentence": [12], "processing.": [13], "Leveraging": [14], "eye-gaze": [15], "data": [16, 113], "from": [17], "the": [18, 24, 62, 66, 106, 115, 135, 140, 146, 177, 193, 208], "English": [19], "and": [20, 51, 92, 213, 224, 230], "Italian": [21], "section": [22], "of": [23, 33, 47, 65, 108, 139, 149, 165, 180, 195], "Multilingual": [25], "Eye-Movement": [26], "Corpus": [27], "(MECO),": [28], "we": [29, 69, 122], "designed": [30], "series": [32], "experiments": [34], "aiming": [35], "at": [36], "exploring": [37], "whether": [38], "pre-trained": [39], "neural": [40], "language": [41, 186, 202], "models": [42, 150, 187], "(NLMs)": [43], "encode": [44, 87], "patterns": [45, 171], "representative": [46], "reading": [49, 212], "behaviour": [50, 219], "if": [52, 73], "directly": [53], "incorporating": [54], "this": [55, 125], "information": [56, 89], "through": [57, 78], "fine-tuning": [59, 110, 153], "process": [60], "influences": [61], "cognitive": [63, 190, 209], "plausibility": [64], "model.": [67], "Additionally,": [68], "sought": [70], "to": [71], "determine": [72], "such": [74], "an": [75], "impact": [76], "persists": [77], "downstream": [80, 120, 142], "task.": [81, 143], "Our": [82], "findings": [83], "reveal": [84], "that": [85, 93, 124, 197], "transformers": [86], "eye-gaze-related": [88], "during": [90], "pretraining": [91], "explicitly": [94], "integrating": [95], "features": [97], "increases": [98], "model": [99, 221], "alignment": [100, 216], "with": [101, 157, 207, 217], "attention.": [103, 159], "When": [104], "investigating": [105], "effect": [107], "intermediate": [109, 126, 152], "on": [111, 114, 118], "model\u2019s": [116], "performance": [117], "task,": [121], "observe": [123], "step": [127], "does": [128], "not": [129, 198], "result": [130], "in": [131, 188], "catastrophic": [132], "forgetting,": [133], "despite": [134], "very": [136], "different": [137], "nature": [138], "considered": [141], "In": [144, 160], "addition,": [145], "attention": [147, 170], "mechanism": [148], "undergoing": [151], "remains": [154], "closely": [155], "aligned": [156], "conclusion,": [161], "our": [162], "comprehensive": [163], "evaluation": [164], "NLMs": [166], "informed": [167], "by": [168], "offers": [172], "great": [173], "potential": [174], "advancing": [176], "growing": [178], "field": [179], "eXplainable": [181], "Artificial": [182], "Intelligence": [183], "(XAI).": [184], "Grounding": [185], "real-world": [189], "processes": [191], "enables": [192], "creation": [194], "systems": [196], "only": [199], "replicate": [200], "output": [203], "but": [204], "also": [205], "align": [206], "mechanisms": [210], "behind": [211], "comprehension.": [214], "This": [215], "enhances": [220], "adaptability,": [222], "interpretability,": [223], "effectiveness,": [225], "fostering": [226], "more": [227], "human-centric,": [228], "transparent,": [229], "reliable": [231], "AI": [232], "applications": [233], "across": [234], "various": [235], "domains.": [236], "1": [237]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5313000082969666, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5313000082969666, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10465", "display_name": "Neurobiology of Language and Bilingualism", "score": 0.18529999256134033, "subfield": {"id": "https://openalex.org/subfields/2805", "display_name": "Cognitive Neuroscience"}, "field": {"id": "https://openalex.org/fields/28", "display_name": "Neuroscience"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.09210000187158585, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.neucom.2025.130617", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.neucom.2025.130617", "pdf_url": null, "source": {"id": "https://openalex.org/S45693802", "display_name": "Neurocomputing", "issn_l": "0925-2312", "issn": ["0925-2312", "1872-8286"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-2", "ki-jl-2", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Neurocomputing", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4407423379", "doi": "https://doi.org/10.48550/arxiv.2502.06892", "title": "Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks", "publication_year": 2025, "publication_date": "2025-02-09", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "He, Bowei", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I168719708", "display_name": "City University of Hong Kong", "ror": "https://ror.org/03q8dnn23", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I168719708"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "He, Bowei", "raw_affiliation_strings": ["City University of Hong Kong , 2 Huawei , Hong Kong ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "City University of Hong Kong , 2 Huawei , Hong Kong ,", "institution_ids": ["https://openalex.org/I168719708"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yin, Lihao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yin, Lihao", "raw_affiliation_strings": ["Noah's Ark Lab , Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Noah's Ark Lab , Hong Kong", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5031170152", "display_name": "Hui\u2010Ling Zhen", "orcid": "https://orcid.org/0000-0003-0310-3825", "observed_orcids": ["https://orcid.org/0000-0003-0310-3825"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhen, Hui-Ling", "raw_affiliation_strings": ["Noah's Ark Lab , Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Noah's Ark Lab , Hong Kong", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101673775", "display_name": "Jianping Zhang", "orcid": "https://orcid.org/0009-0000-8763-7407", "observed_orcids": ["https://orcid.org/0009-0000-8763-7407"]}, "institutions": [{"id": "https://openalex.org/I177725633", "display_name": "Chinese University of Hong Kong", "ror": "https://ror.org/00t33hh48", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I177725633"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Zhang, Jianping", "raw_affiliation_strings": ["The Chinese University of Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Chinese University of Hong Kong", "institution_ids": ["https://openalex.org/I177725633"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003882618", "display_name": "Lanqing Hong", "orcid": "https://orcid.org/0000-0003-2752-5942", "observed_orcids": ["https://orcid.org/0000-0003-2752-5942"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hong, Lanqing", "raw_affiliation_strings": ["Noah's Ark Lab , Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Noah's Ark Lab , Hong Kong", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109233250", "display_name": "Mingxuan Yuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yuan, Mingxuan", "raw_affiliation_strings": ["Noah's Ark Lab , Hong Kong"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Noah's Ark Lab , Hong Kong", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100514620", "display_name": "Chen Ma", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I168719708", "display_name": "City University of Hong Kong", "ror": "https://ror.org/03q8dnn23", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I168719708"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Ma, Chen", "raw_affiliation_strings": ["City University of Hong Kong , 2 Huawei , Hong Kong ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "City University of Hong Kong , 2 Huawei , Hong Kong ,", "institution_ids": ["https://openalex.org/I168719708"]}]}], "abstract_inverted_index": {"The": [0], "widespread": [1], "deployment": [2], "of": [3, 54, 60, 169], "pre-trained": [4], "language": [5, 83], "models": [6], "(PLMs)": [7], "has": [8], "exposed": [9], "them": [10], "to": [11, 27, 62, 108, 131, 151], "textual": [12, 55, 111], "backdoor": [13, 87], "attacks,": [14], "particularly": [15], "those": [16], "planted": [17], "during": [18, 135], "the": [19, 50, 58, 114, 127], "pre-training": [20, 65], "stage.": [21], "These": [22], "attacks": [23], "pose": [24], "significant": [25], "risks": [26], "high-reliability": [28], "applications,": [29], "as": [30], "they": [31], "can": [32], "stealthily": [33], "affect": [34], "multiple": [35], "downstream": [36], "tasks.": [37], "While": [38], "certifying": [39, 82], "robustness": [40, 85, 92, 148], "against": [41, 86], "such": [42], "threats": [43], "is": [44], "crucial,": [45], "existing": [46, 152], "defenses": [47], "struggle": [48], "with": [49, 95], "high-dimensional,": [51], "interdependent": [52], "nature": [53], "data": [56, 134], "and": [57, 121, 161, 173], "lack": [59], "access": [61, 130], "original": [63], "poisoned": [64, 132], "data.": [66], "To": [67], "address": [68], "these": [69], "challenges,": [70], "we": [71], "introduce": [72], "\\textbf{F}uzzed": [73], "\\textbf{R}andomized": [74], "\\textbf{S}moothing": [75], "(\\textbf{FRS}),": [76], "a": [77, 145], "novel": [78], "approach": [79], "for": [80, 105, 119, 129], "efficiently": [81], "model": [84, 97, 136, 159], "attacks.": [88], "FRS": [89, 143], "integrates": [90], "software": [91], "certification": [93], "techniques": [94], "biphased": [96], "parameter": [98], "smoothing,": [99], "employing": [100], "Monte": [101], "Carlo": [102], "tree": [103], "search": [104], "proactive": [106], "fuzzing": [107], "identify": [109], "vulnerable": [110], "segments": [112], "within": [113], "Damerau-Levenshtein": [115], "space.": [116], "This": [117], "allows": [118], "targeted": [120], "efficient": [122], "text": [123], "randomization,": [124], "while": [125], "eliminating": [126], "need": [128], "training": [133], "smoothing.": [137], "Our": [138], "theoretical": [139], "analysis": [140], "demonstrates": [141], "that": [142], "achieves": [144], "broader": [146], "certified": [147], "radius": [149], "compared": [150], "methods.": [153], "Extensive": [154], "experiments": [155], "across": [156], "various": [157], "datasets,": [158], "configurations,": [160], "attack": [162], "strategies": [163], "validate": [164], "FRS's": [165], "superiority": [166], "in": [167], "terms": [168], "defense": [170], "efficiency,": [171], "accuracy,": [172], "robustness.": [174]}, "primary_topic": {"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11424", "display_name": "Security and Verification in Computing", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1712", "display_name": "Software"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.06892", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.06892", "pdf_url": "https://arxiv.org/pdf/2502.06892", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416445992", "doi": "https://doi.org/10.48550/arxiv.2505.15922", "title": "Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition", "publication_year": 2025, "publication_date": "2025-05-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100398178", "display_name": "Dong Won Lee", "orcid": "https://orcid.org/0000-0002-6336-5512", "observed_orcids": ["https://orcid.org/0000-0002-6336-5512"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lee, Dong Won", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102016303", "display_name": "Hae Won Park", "orcid": "https://orcid.org/0000-0001-9638-1722", "observed_orcids": ["https://orcid.org/0000-0001-9638-1722"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Park, Hae Won", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5108541589", "display_name": "Cynthia Breazeal", "orcid": "https://orcid.org/0000-0002-0587-2065", "observed_orcids": ["https://orcid.org/0000-0002-0587-2065"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Breazeal, Cynthia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5112302512", "display_name": "Louis-Philippe Morency", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Morency, Louis-Philippe", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0, 21, 101], "propose": [1], "a": [2, 16, 27, 88], "large": [3, 30], "language": [4, 31, 79], "model": [5, 32], "based": [6], "reward": [7, 54, 90, 110, 128, 136], "decomposition": [8, 55, 111], "framework": [9], "for": [10, 95, 98, 134], "aligning": [11], "dialogue": [12, 59, 99], "agents": [13], "using": [14, 56], "only": [15, 57], "single": [17], "session-level": [18, 43], "feedback": [19], "signal.": [20], "leverage": [22], "the": [23, 50, 58, 132], "reasoning": [24], "capabilities": [25], "of": [26, 120], "frozen,": [28], "pretrained": [29], "(LLM)": [33], "to": [34, 52], "infer": [35], "fine-grained": [36], "local": [37], "implicit": [38], "rewards": [39, 84], "by": [40], "decomposing": [41], "global,": [42], "feedback.": [44, 141], "Our": [45], "first": [46], "\\emph{text-only}": [47], "variant": [48, 64], "prompts": [49], "LLM": [51], "perform": [53], "transcript.": [60], "The": [61], "second": [62], "\\emph{multimodal}": [63], "incorporates": [65], "additional": [66], "behavioral": [67], "cues,": [68], "such": [69], "as": [70, 77], "pitch,": [71], "gaze,": [72], "and": [73, 105, 113, 138], "facial": [74], "affect,": [75], "expressed": [76], "natural": [78], "descriptions.": [80], "These": [81], "inferred": [82], "turn-level": [83], "are": [85, 126], "distilled": [86], "into": [87], "lightweight": [89], "model,": [91], "which": [92], "we": [93], "utilize": [94], "RL-based": [96], "fine-tuning": [97], "generation.": [100], "evaluate": [102], "both": [103], "text-only": [104], "multimodal": [106], "variants": [107], "against": [108], "state-of-the-art": [109], "methods": [112], "demonstrate": [114], "notable": [115], "improvements": [116], "in": [117], "human": [118, 140], "evaluations": [119], "conversation": [121], "quality,": [122], "suggesting": [123], "that": [124, 130], "LLMs": [125], "strong": [127], "decomposers": [129], "obviate": [131], "need": [133], "manual": [135], "shaping": [137], "granular": [139]}, "primary_topic": {"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.0003000000142492354, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11902", "display_name": "Intelligent Tutoring Systems and Adaptive Learning", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2505.15922", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.15922", "pdf_url": "https://arxiv.org/pdf/2505.15922", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-nc", "license_id": "https://openalex.org/licenses/cc-by-nc", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415183329", "doi": "https://doi.org/10.48550/arxiv.2506.21393", "title": "TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding", "publication_year": 2025, "publication_date": "2025-06-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5108046750", "display_name": "Junwen Zhang", "orcid": "https://orcid.org/0000-0001-8041-1608", "observed_orcids": ["https://orcid.org/0000-0001-8041-1608"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Junwen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100704521", "display_name": "Pu Chen", "orcid": "https://orcid.org/0000-0002-9659-8697", "observed_orcids": ["https://orcid.org/0000-0002-9659-8697", "https://orcid.org/0000-0002-5114-5942", "https://orcid.org/0000-0001-7412-6501"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Pu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100343699", "display_name": "Yin Zhang", "orcid": "https://orcid.org/0000-0001-6986-4227", "observed_orcids": ["https://orcid.org/0000-0001-6986-4227"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Multimodal": [0], "understanding": [1], "of": [2, 13, 124, 187, 208], "tables": [3], "in": [4, 44], "real-world": [5, 160], "contexts": [6], "is": [7], "challenging": [8, 146], "due": [9], "to": [10, 96, 156], "the": [11, 119, 184, 206], "complexity": [12], "structure,": [14], "symbolic": [15, 109], "density,": [16], "and": [17, 47, 91, 132, 143, 152, 163, 190, 202], "visual": [18], "degradation": [19, 162], "(blur,": [20], "skew,": [21], "watermarking,": [22], "incomplete": [23], "structures": [24], "or": [25, 28], "fonts,": [26], "multi-span": [27], "hierarchically": [29], "nested": [30], "layouts).": [31], "Existing": [32], "multimodal": [33, 69, 161, 213], "large": [34], "language": [35], "models": [36, 158], "(MLLMs)": [37], "struggle": [38], "with": [39], "such": [40], "WildStruct": [41, 147], "conditions,": [42], "resulting": [43], "limited": [45], "performance": [46], "poor": [48], "generalization.": [49], "To": [50, 112], "address": [51], "these": [52], "challenges,": [53], "we": [54, 117, 141, 197], "propose": [55], "TableMoE,": [56], "a": [57, 103], "neuro-symbolic": [58, 210], "Mixture-of-Connector-Experts": [59], "(MoCE)": [60], "architecture": [61], "specifically": [62, 155], "designed": [63, 154], "for": [64, 136, 212], "robust,": [65], "structured": [66, 191], "reasoning": [67, 110, 211], "over": [68], "table": [70, 94, 214], "data.": [71], "TableMoE": [72, 170], "features": [73], "an": [74], "innovative": [75], "Neuro-Symbolic": [76, 188], "Routing": [77, 189], "mechanism,": [78], "which": [79], "predicts": [80], "latent": [81], "semantic": [82], "token": [83], "roles": [84], "(e.g.,": [85], "header,": [86], "data": [87], "cell,": [88], "axis,": [89], "formula)": [90], "dynamically": [92], "routes": [93], "elements": [95], "specialized": [97], "experts": [98], "(Table-to-HTML,": [99], "Table-to-JSON,": [100], "Table-to-Code)": [101], "using": [102], "confidence-aware": [104], "gating": [105], "strategy": [106], "informed": [107], "by": [108], "graphs.": [111], "facilitate": [113], "effective": [114], "alignment-driven": [115], "pretraining,": [116], "introduce": [118], "large-scale": [120], "TableMoE-Align": [121], "dataset,": [122], "consisting": [123], "1.2M": [125], "table-HTML-JSON-code": [126], "quadruples": [127], "across": [128], "finance,": [129], "science,": [130], "biomedicine": [131], "industry,": [133], "utilized": [134], "exclusively": [135], "model": [137], "pretraining.": [138], "For": [139], "evaluation,": [140], "curate": [142], "release": [144], "four": [145], "benchmarks:": [148], "WMMFinQA,": [149], "WMMTatQA,": [150], "WMMTabDialog,": [151], "WMMFinanceMath,": [153], "stress-test": [157], "under": [159], "structural": [164], "complexity.": [165], "Experimental": [166], "results": [167], "demonstrate": [168], "that": [169], "significantly": [171], "surpasses": [172], "existing": [173], "state-of-the-art": [174], "models.": [175], "Extensive": [176], "ablation": [177], "studies": [178], "validate": [179], "each": [180], "core": [181], "component,": [182], "emphasizing": [183], "critical": [185], "role": [186], "expert": [192], "alignment.": [193], "Through": [194], "qualitative": [195], "analyses,": [196], "further": [198], "showcase": [199], "TableMoE's": [200], "interpretability": [201], "enhanced": [203], "robustness,": [204], "underscoring": [205], "effectiveness": [207], "integrating": [209], "understanding.": [215]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9595000147819519, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10601", "display_name": "Handwritten Text Recognition Techniques", "score": 0.02319999970495701, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.005900000222027302, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2506.21393", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.21393", "pdf_url": "https://arxiv.org/pdf/2506.21393", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4408105557", "doi": "https://doi.org/10.1016/j.frl.2025.106967", "title": "AT-FinGPT: Financial risk prediction via an audio-text large language model", "publication_year": 2025, "publication_date": "2025-03-03", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yingnan Liu", "orcid": "https://orcid.org/0000-0002-4221-5603", "observed_orcids": ["https://orcid.org/0000-0002-4221-5603"]}, "institutions": [{"id": "https://openalex.org/I109935558", "display_name": "Ningbo University", "ror": "https://ror.org/03et85d35", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I109935558"]}, {"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "government", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210165339", "display_name": "Ningbo Institute of Industrial Technology", "ror": "https://ror.org/05nqg3g04", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yingnan Liu", "raw_affiliation_strings": ["Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "School of Business, Ningbo University, Ningbo, 315211, China", "School of Law, Ningbo University, Ningbo, 315211, China"], "raw_orcid": "https://orcid.org/0000-0002-4221-5603", "affiliations": [{"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "School of Business, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}, {"raw_affiliation_string": "School of Law, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5080306994", "display_name": "Ningbo Bu", "orcid": "https://orcid.org/0000-0003-3171-9715", "observed_orcids": ["https://orcid.org/0000-0003-3171-9715"]}, "institutions": [{"id": "https://openalex.org/I109935558", "display_name": "Ningbo University", "ror": "https://ror.org/03et85d35", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I109935558"]}, {"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "government", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210165339", "display_name": "Ningbo Institute of Industrial Technology", "ror": "https://ror.org/05nqg3g04", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ningbo Bu", "raw_affiliation_strings": ["Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "School of Business, Ningbo University, Ningbo, 315211, China", "School of Law, Ningbo University, Ningbo, 315211, China"], "raw_orcid": "https://orcid.org/0000-0003-3171-9715", "affiliations": [{"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "School of Business, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}, {"raw_affiliation_string": "School of Law, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhiqiang Li", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I109935558", "display_name": "Ningbo University", "ror": "https://ror.org/03et85d35", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I109935558"]}, {"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "government", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210165339", "display_name": "Ningbo Institute of Industrial Technology", "ror": "https://ror.org/05nqg3g04", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhiqiang Li", "raw_affiliation_strings": ["Donghai Laboratory, Zhoushan, 316021, China", "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "School of Business, Ningbo University, Ningbo, 315211, China", "School of Law, Ningbo University, Ningbo, 315211, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Donghai Laboratory, Zhoushan, 316021, China", "institution_ids": []}, {"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "School of Business, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}, {"raw_affiliation_string": "School of Law, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yongmin Zhang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I109935558", "display_name": "Ningbo University", "ror": "https://ror.org/03et85d35", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I109935558"]}, {"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "government", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210165339", "display_name": "Ningbo Institute of Industrial Technology", "ror": "https://ror.org/05nqg3g04", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yongmin Zhang", "raw_affiliation_strings": ["Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "School of Business, Ningbo University, Ningbo, 315211, China", "School of Law, Ningbo University, Ningbo, 315211, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "School of Business, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}, {"raw_affiliation_string": "School of Law, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101861830", "display_name": "Zhenyu Zhao", "orcid": "https://orcid.org/0000-0002-1041-2995", "observed_orcids": ["https://orcid.org/0000-0002-1041-2995"]}, "institutions": [{"id": "https://openalex.org/I109935558", "display_name": "Ningbo University", "ror": "https://ror.org/03et85d35", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I109935558"]}, {"id": "https://openalex.org/I19820366", "display_name": "Chinese Academy of Sciences", "ror": "https://ror.org/034t30j35", "country_code": "CN", "type": "government", "lineage": ["https://openalex.org/I19820366"]}, {"id": "https://openalex.org/I4210165339", "display_name": "Ningbo Institute of Industrial Technology", "ror": "https://ror.org/05nqg3g04", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Zhenyu Zhao", "raw_affiliation_strings": ["Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "School of Business, Ningbo University, Ningbo, 315211, China", "School of Law, Ningbo University, Ningbo, 315211, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Laboratory of Robotics and Intelligent Manufacturing Equipment Technology, Ningbo Institute of Materials Technology and Engineering, (NlMTE) of the Chinese Academy of Sciences (CAS), Ningbo, 315201, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210165339"]}, {"raw_affiliation_string": "School of Business, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}, {"raw_affiliation_string": "School of Law, Ningbo University, Ningbo, 315211, China", "institution_ids": ["https://openalex.org/I109935558"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11653", "display_name": "Financial Distress and Bankruptcy Prediction", "score": 0.5776000022888184, "subfield": {"id": "https://openalex.org/subfields/1402", "display_name": "Accounting"}, "field": {"id": "https://openalex.org/fields/14", "display_name": "Business, Management and Accounting"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T11653", "display_name": "Financial Distress and Bankruptcy Prediction", "score": 0.5776000022888184, "subfield": {"id": "https://openalex.org/subfields/1402", "display_name": "Accounting"}, "field": {"id": "https://openalex.org/fields/14", "display_name": "Business, Management and Accounting"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11326", "display_name": "Stock Market Forecasting Methods", "score": 0.36469998955726624, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.011500000022351742, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.frl.2025.106967", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.frl.2025.106967", "pdf_url": null, "source": {"id": "https://openalex.org/S88577320", "display_name": "Finance research letters", "issn_l": "1544-6123", "issn": ["1544-6123", "1544-6131"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["abdc-a", "cwts-core", "jufo-1", "norway-1"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Finance Research Letters", "raw_type": "journal-article"}, "cited_by_count": 27, "is_retracted": false}, {"id": "https://openalex.org/W4415217940", "doi": "https://doi.org/10.1016/j.mcpdig.2025.100296", "title": "Identifying Bias at Scale in Clinical Notes Using Large Language Models", "publication_year": 2025, "publication_date": "2025-10-15", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5012807122", "display_name": "Donald U. Apakama", "orcid": "https://orcid.org/0000-0001-6217-1620", "observed_orcids": ["https://orcid.org/0000-0001-6217-1620"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Donald U. Apakama", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY", "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016800014", "display_name": "Kim-Anh-Nhi Nguyen", "orcid": "https://orcid.org/0000-0002-3446-9750", "observed_orcids": ["https://orcid.org/0000-0002-3446-9750"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Kim-Anh-Nhi Nguyen", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114404030", "display_name": "Daphnee Hyppolite", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I1320796813", "display_name": "Mount Sinai Health System", "ror": "https://ror.org/04kfn4587", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1320796813"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Daphnee Hyppolite", "raw_affiliation_strings": ["Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY", "institution_ids": ["https://openalex.org/I1320796813"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079561272", "display_name": "Shelly Soffer", "orcid": "https://orcid.org/0000-0002-7853-2029", "observed_orcids": ["https://orcid.org/0000-0002-7853-2029"]}, "institutions": [{"id": "https://openalex.org/I2800389475", "display_name": "Rabin Medical Center", "ror": "https://ror.org/01vjtf564", "country_code": "IL", "type": "healthcare", "lineage": ["https://openalex.org/I2800389475", "https://openalex.org/I64767286"]}], "countries": ["IL"], "is_corresponding": true, "raw_author_name": "Shelly Soffer", "raw_affiliation_strings": ["Institute of Hematology, Davidoff Cancer Center, Rabin Medical Center Petah-Tikva, Israel"], "raw_orcid": "https://orcid.org/0000-0002-7853-2029", "affiliations": [{"raw_affiliation_string": "Institute of Hematology, Davidoff Cancer Center, Rabin Medical Center Petah-Tikva, Israel", "institution_ids": ["https://openalex.org/I2800389475"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5095921818", "display_name": "Aya Mudrik", "orcid": "https://orcid.org/0009-0002-3429-9242", "observed_orcids": ["https://orcid.org/0009-0002-3429-9242"]}, "institutions": [{"id": "https://openalex.org/I124227911", "display_name": "Ben-Gurion University of the Negev", "ror": "https://ror.org/05tkyf982", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I124227911"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Aya Mudrik", "raw_affiliation_strings": ["Ben-Gurion University of the Negev, Be'er Sheva, Israel"], "raw_orcid": "https://orcid.org/0009-0002-3429-9242", "affiliations": [{"raw_affiliation_string": "Ben-Gurion University of the Negev, Be'er Sheva, Israel", "institution_ids": ["https://openalex.org/I124227911"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Emilia Ling", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Emilia Ling", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Akini Moses", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Akini Moses", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114404031", "display_name": "Ivanka Temnycky", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ivanka Temnycky", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Allison Glasser", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I1320796813", "display_name": "Mount Sinai Health System", "ror": "https://ror.org/04kfn4587", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1320796813"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Allison Glasser", "raw_affiliation_strings": ["Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY", "institution_ids": ["https://openalex.org/I1320796813"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5017430360", "display_name": "Rebecca Anderson", "orcid": "https://orcid.org/0000-0001-8925-7002", "observed_orcids": ["https://orcid.org/0000-0001-8925-7002"]}, "institutions": [{"id": "https://openalex.org/I1320796813", "display_name": "Mount Sinai Health System", "ror": "https://ror.org/04kfn4587", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1320796813"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Rebecca Anderson", "raw_affiliation_strings": ["Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Office of the Chief Medical Officer, Mount Sinai Health System, New York, NY", "institution_ids": ["https://openalex.org/I1320796813"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038896342", "display_name": "Prathamesh Parchure", "orcid": "https://orcid.org/0009-0001-9383-691X", "observed_orcids": ["https://orcid.org/0009-0001-9383-691X"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Prathamesh Parchure", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114404029", "display_name": "Evajoyce Woullard", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Evajoyce Woullard", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5054823755", "display_name": "Masoud Edalati", "orcid": "https://orcid.org/0000-0002-1132-9480", "observed_orcids": ["https://orcid.org/0000-0002-1132-9480"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Masoud Edalati", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5059085082", "display_name": "Lili Chan", "orcid": "https://orcid.org/0000-0003-4300-5760", "observed_orcids": ["https://orcid.org/0000-0003-4300-5760"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Lili Chan", "raw_affiliation_strings": ["The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5027333200", "display_name": "Clair A. Kronk", "orcid": "https://orcid.org/0000-0001-8397-8810", "observed_orcids": ["https://orcid.org/0000-0001-8397-8810"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Clair Kronk", "raw_affiliation_strings": ["Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5070462882", "display_name": "Robert M. Freeman", "orcid": "https://orcid.org/0000-0003-4946-6533", "observed_orcids": ["https://orcid.org/0000-0003-4946-6533"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Robert Freeman", "raw_affiliation_strings": ["The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5004797900", "display_name": "Arash Negahdari Kia", "orcid": "https://orcid.org/0000-0002-3675-0239", "observed_orcids": ["https://orcid.org/0000-0002-3675-0239"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Arash Kia", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5021533090", "display_name": "Prem Timsina", "orcid": "https://orcid.org/0000-0002-6047-887X", "observed_orcids": ["https://orcid.org/0000-0002-6047-887X"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Prem Timsina", "raw_affiliation_strings": ["Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089697111", "display_name": "Matthew A. Levin", "orcid": "https://orcid.org/0000-0002-6013-2684", "observed_orcids": ["https://orcid.org/0000-0002-6013-2684"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Matthew A. Levin", "raw_affiliation_strings": ["Department of Anesthesiology, Perioperative and Pain Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY", "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Anesthesiology, Perioperative and Pain Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5017974764", "display_name": "Rohan Khera", "orcid": "https://orcid.org/0000-0001-9467-6199", "observed_orcids": ["https://orcid.org/0000-0001-9467-6199"]}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Rohan Khera", "raw_affiliation_strings": ["Department of Medicine, Yale University School of Medicine New Haven, CT"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Medicine, Yale University School of Medicine New Haven, CT", "institution_ids": ["https://openalex.org/I32971472"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019842052", "display_name": "Patricia Kovatch", "orcid": "https://orcid.org/0000-0001-8368-1742", "observed_orcids": ["https://orcid.org/0000-0001-8368-1742"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Patricia Kovatch", "raw_affiliation_strings": ["Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091224898", "display_name": "Alexander W. Charney", "orcid": "https://orcid.org/0000-0001-8135-6858", "observed_orcids": ["https://orcid.org/0000-0001-8135-6858"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Alexander W. Charney", "raw_affiliation_strings": ["Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY", "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024282536", "display_name": "Brendan G. Carr", "orcid": "https://orcid.org/0000-0002-9147-9701", "observed_orcids": ["https://orcid.org/0000-0002-9147-9701"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Brendan G. Carr", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5075743971", "display_name": "Lynne D. Richardson", "orcid": "https://orcid.org/0000-0002-5425-1601", "observed_orcids": ["https://orcid.org/0000-0002-5425-1601"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Lynne D. Richardson", "raw_affiliation_strings": ["Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY", "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Emergency Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5110836986", "display_name": "Carol R. Horowitz", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Carol R. Horowitz", "raw_affiliation_strings": ["Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY", "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "Institute for Health Equity Research, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039899830", "display_name": "Eyal Klang", "orcid": "https://orcid.org/0000-0002-4567-3108", "observed_orcids": ["https://orcid.org/0000-0002-4567-3108"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Eyal Klang", "raw_affiliation_strings": ["The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5047405500", "display_name": "Girish N. Nadkarni", "orcid": "https://orcid.org/0000-0001-6319-4314", "observed_orcids": ["https://orcid.org/0000-0001-6319-4314"]}, "institutions": [{"id": "https://openalex.org/I98704320", "display_name": "Icahn School of Medicine at Mount Sinai", "ror": "https://ror.org/04a9tmd77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I1320796813", "https://openalex.org/I98704320"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Girish N. Nadkarni", "raw_affiliation_strings": ["The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Charles Bronfman Department of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}, {"raw_affiliation_string": "The Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY", "institution_ids": ["https://openalex.org/I98704320"]}]}], "abstract_inverted_index": {"Objective:": [0], "To": [1], "evaluate": [2], "whether": [3], "generative": [4], "pretrained": [5], "transformer": [6], "(GPT)-4": [7], "can": [8], "detect": [9], "and": [10, 23, 33, 41, 84, 102, 113, 136, 156, 193, 251, 262], "revise": [11], "biased": [12, 30, 205, 240], "language": [13, 124, 145, 241], "in": [14, 147, 242, 265], "emergency": [15], "department": [16], "(ED)": [17], "notes,": [18, 244], "against": [19], "human-adjudicated": [20], "gold-standard": [21], "labels,": [22], "to": [24, 53, 97, 120, 211, 248], "identify": [25], "modifiable": [26, 246], "factors": [27], "associated": [28], "with": [29, 140], "documentation.": [31, 206], "Patients": [32], "Methods:": [34], "We": [35, 57, 92, 116], "randomly": [36, 59], "sampled": [37, 60], "50,000": [38], "ED": [39], "medical": [40], "nursing": [42], "notes": [43, 63, 155], "from": [44, 64], "the": [45, 65, 141], "Mount": [46, 153], "Sinai": [47, 154], "Health": [48], "System": [49], "(January": [50], "1,": [51], "2023,": [52], "December": [54], "31,": [55], "2023).": [56], "also": [58], "500": [61], "discharge": [62], "Medical": [66, 162], "Information": [67, 163], "Mart": [68, 164], "for": [69, 165], "Intensive": [70, 166], "Care": [71, 167], "IV": [72, 168], "database.": [73], "The": [74, 131, 233], "GPT-4": [75, 132, 237], "flagged": [76], "4": [77], "types": [78], "of": [79, 150, 152, 159, 161, 204, 230], "bias:": [80], "discrediting,": [81], "stigmatizing/labeling,": [82], "judgmental,": [83], "stereotyping.": [85], "Two": [86], "human": [87, 142], "reviewers": [88], "verified": [89], "model": [90], "detections.": [91], "used": [93], "multivariable": [94], "logistic": [95], "regression": [96], "examine": [98], "associations": [99], "between": [100], "bias": [101, 213, 261], "health": [103, 174], "care": [104, 175], "utilization,": [105], "presenting": [106], "problems": [107], "(eg,": [108], "substance": [109, 185], "use),": [110], "shift": [111], "timing,": [112], "provider": [114], "type.": [115], "then": [117], "asked": [118], "physicians": [119], "rate": [121], "GPT-4's": [122, 221], "proposed": [123], "revisions": [125, 223], "on": [126], "a": [127], "10-point": [128], "scale.": [129], "Results:": [130], "showed": [133, 201, 235], "97.6%": [134], "sensitivity": [135], "85.7%": [137], "specificity": [138], "compared": [139], "review.": [143], "Biased": [144], "appeared": [146], "6.5%": [148], "(3229": [149], "50,000)": [151], "7.4%": [157], "(37": [158], "500)": [160], "notes.": [169], "In": [170], "adjusted": [171], "models,": [172], "frequent": [173], "utilization": [176], "(adjusted": [177], "odds": [178, 203], "ratio": [179], "[aOR],": [180], "2.85;": [181], "95%": [182, 190, 198, 218], "CI,": [183, 191, 199, 219], "1.95-4.17),": [184], "use": [186], "presentations": [187], "(aOR,": [188, 196, 216], "3.09;": [189], "2.51-3.80),": [192], "overnight": [194], "shifts": [195], "1.37;": [197], "1.23-1.52)": [200], "elevated": [202], "Physicians": [207], "were": [208], "more": [209], "likely": [210], "include": [212], "than": [214], "nurses": [215], "2.26;": [217], "2.07-2.46);": [220], "recommended": [222], "received": [224], "mean": [225], "physician": [226], "ratings": [227], "above": [228], "9": [229], "10.": [231], "Conclusion:": [232], "study": [234], "that": [236, 249], "accurately": [238], "detects": [239], "clinical": [243], "identifies": [245], "contributors": [247], "bias,": [250], "delivers": [252], "physician-endorsed": [253], "revisions.": [254], "This": [255], "approach": [256], "may": [257], "help": [258], "mitigate": [259], "documentation": [260], "reduce": [263], "disparities": [264], "care.": [266]}, "primary_topic": {"id": "https://openalex.org/T10883", "display_name": "Ethics and Social Impacts of AI", "score": 0.46239998936653137, "subfield": {"id": "https://openalex.org/subfields/3311", "display_name": "Safety Research"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T10883", "display_name": "Ethics and Social Impacts of AI", "score": 0.46239998936653137, "subfield": {"id": "https://openalex.org/subfields/3311", "display_name": "Safety Research"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.21580000221729279, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.09939999878406525, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.mcpdig.2025.100296", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.mcpdig.2025.100296", "pdf_url": "https://www.mcpdigitalhealth.org/article/S2949-7612(25)00103-8/pdf", "source": {"id": "https://openalex.org/S4387287143", "display_name": "Mayo Clinic Proceedings Digital Health", "issn_l": "2949-7612", "issn": ["2949-7612"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "jufo-1", "ki-jl-1", "norway-1"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Mayo Clinic Proceedings: Digital Health", "raw_type": "journal-article"}, "cited_by_count": 5, "is_retracted": false}, {"id": "https://openalex.org/W4410738052", "doi": "https://doi.org/10.1109/tpami.2025.3573609", "title": "LLaFS++: Few-Shot Image Segmentation With Large Language Models", "publication_year": 2025, "publication_date": "2025-05-26", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5074956841", "display_name": "Lanyun Zhu", "orcid": "https://orcid.org/0000-0001-7309-3330", "observed_orcids": ["https://orcid.org/0000-0001-7309-3330"]}, "institutions": [{"id": "https://openalex.org/I152815399", "display_name": "Singapore University of Technology and Design", "ror": "https://ror.org/05j6fvn87", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I152815399"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Lanyun Zhu", "raw_affiliation_strings": ["Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore"], "raw_orcid": "https://orcid.org/0000-0001-7309-3330", "affiliations": [{"raw_affiliation_string": "Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore", "institution_ids": ["https://openalex.org/I152815399"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5054714748", "display_name": "Tianrun Chen", "orcid": "https://orcid.org/0000-0003-0177-0157", "observed_orcids": ["https://orcid.org/0000-0003-0177-0157"]}, "institutions": [{"id": "https://openalex.org/I76130692", "display_name": "Zhejiang University", "ror": "https://ror.org/00a2xv884", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I76130692"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tianrun Chen", "raw_affiliation_strings": ["College of Computer Science and Technology, Zhejiang University, Hangzhou, China", "College of Computer Science and Technology, Zhejiang University, China"], "raw_orcid": "https://orcid.org/0000-0003-0177-0157", "affiliations": [{"raw_affiliation_string": "College of Computer Science and Technology, Zhejiang University, Hangzhou, China", "institution_ids": ["https://openalex.org/I76130692"]}, {"raw_affiliation_string": "College of Computer Science and Technology, Zhejiang University, China", "institution_ids": ["https://openalex.org/I76130692"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089146499", "display_name": "Deyi Ji", "orcid": "https://orcid.org/0000-0001-7561-9789", "observed_orcids": ["https://orcid.org/0000-0001-7561-9789"]}, "institutions": [{"id": "https://openalex.org/I45928872", "display_name": "Alibaba Group (China)", "ror": "https://ror.org/00k642b80", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I45928872"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Deyi Ji", "raw_affiliation_strings": ["Alibaba Cloud Computing, Beijing, China", "Alibaba Group, China"], "raw_orcid": "https://orcid.org/0000-0001-7561-9789", "affiliations": [{"raw_affiliation_string": "Alibaba Cloud Computing, Beijing, China", "institution_ids": ["https://openalex.org/I45928872"]}, {"raw_affiliation_string": "Alibaba Group, China", "institution_ids": ["https://openalex.org/I45928872"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Peng Xu", "orcid": "https://orcid.org/0009-0005-5545-4530", "observed_orcids": ["https://orcid.org/0009-0005-5545-4530"]}, "institutions": [{"id": "https://openalex.org/I45928872", "display_name": "Alibaba Group (China)", "ror": "https://ror.org/00k642b80", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I45928872"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Peng Xu", "raw_affiliation_strings": ["Alibaba Cloud Computing, Beijing, China", "Alibaba Group, China"], "raw_orcid": "https://orcid.org/0009-0005-5545-4530", "affiliations": [{"raw_affiliation_string": "Alibaba Cloud Computing, Beijing, China", "institution_ids": ["https://openalex.org/I45928872"]}, {"raw_affiliation_string": "Alibaba Group, China", "institution_ids": ["https://openalex.org/I45928872"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010419481", "display_name": "Jieping Ye", "orcid": "https://orcid.org/0000-0001-8662-5818", "observed_orcids": ["https://orcid.org/0000-0001-8662-5818"]}, "institutions": [{"id": "https://openalex.org/I45928872", "display_name": "Alibaba Group (China)", "ror": "https://ror.org/00k642b80", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I45928872"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jieping Ye", "raw_affiliation_strings": ["Alibaba Cloud Computing, Beijing, China", "Alibaba Group, China"], "raw_orcid": "https://orcid.org/0000-0001-8662-5818", "affiliations": [{"raw_affiliation_string": "Alibaba Cloud Computing, Beijing, China", "institution_ids": ["https://openalex.org/I45928872"]}, {"raw_affiliation_string": "Alibaba Group, China", "institution_ids": ["https://openalex.org/I45928872"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100361857", "display_name": "Jun Liu", "orcid": "https://orcid.org/0000-0002-4365-4165", "observed_orcids": ["https://orcid.org/0000-0002-4365-4165"]}, "institutions": [{"id": "https://openalex.org/I67415387", "display_name": "Lancaster University", "ror": "https://ror.org/04f2nsd36", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I67415387"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Jun Liu", "raw_affiliation_strings": ["School of Computing and Communications, Lancaster University, Lancaster, U.K", "School of Computing and Communications, Lancaster University, U.K"], "raw_orcid": "https://orcid.org/0000-0002-4365-4165", "affiliations": [{"raw_affiliation_string": "School of Computing and Communications, Lancaster University, Lancaster, U.K", "institution_ids": ["https://openalex.org/I67415387"]}, {"raw_affiliation_string": "School of Computing and Communications, Lancaster University, U.K", "institution_ids": ["https://openalex.org/I67415387"]}]}], "abstract_inverted_index": {"Despite": [0], "the": [1, 21, 61, 77, 86, 92, 97, 108, 111, 125, 136, 154, 193, 221], "rapid": [2], "advancements": [3], "in": [4, 12, 96, 114], "few-shot": [5, 98, 229], "segmentation": [6, 87, 141], "(FSS),": [7], "most": [8], "of": [9, 31, 45, 110, 224], "existing": [10], "methods": [11], "this": [13, 49, 51], "domain": [14], "are": [15], "hampered": [16], "by": [17, 82, 192], "their": [18, 38], "reliance": [19], "on": [20, 209], "limited": [22, 93], "and": [23, 71, 101, 121, 146, 158, 167, 176, 180, 215], "biased": [24], "information": [25, 94], "from": [26], "only": [27], "a": [28, 54, 148, 182], "small": [29], "number": [30], "labeled": [32, 99], "samples.": [33], "This": [34], "limitation": [35], "inherently": [36], "restricts": [37], "capability": [39], "to": [40, 84, 138, 152, 173, 186, 227], "achieve": [41, 177], "sufficiently": [42], "high": [43], "levels": [44], "performance.": [46], "To": [47, 106], "address": [48], "issue,": [50], "paper": [52], "proposes": [53], "pioneering": [55], "framework": [56, 204], "named": [57], "LLaFS++,": [58], "which,": [59], "for": [60, 91, 171], "first": [62], "time,": [63], "applies": [64], "large": [65], "language": [66], "models": [67], "(LLMs)": [68], "into": [69], "FSS": [70, 115], "achieves": [72, 206], "notable": [73], "success.": [74], "LLaFS++": [75, 126, 200], "leverages": [76], "extensive": [78], "prior": [79], "knowledge": [80], "embedded": [81], "LLMs": [83, 113, 226], "guide": [85], "process,": [88], "effectively": [89], "compensating": [90], "contained": [95], "samples": [100, 166], "thereby": [102], "achieving": [103], "superior": [104, 218], "results.": [105], "enhance": [107], "effectiveness": [109], "text-based": [112], "scenarios,": [116], "we": [117, 129], "present": [118], "several": [119], "innovative": [120], "task-specific": [122], "designs": [123], "within": [124], "framework.": [127], "Specifically,": [128], "introduce": [130], "an": [131, 202], "input": [132], "instruction": [133], "that": [134, 205], "allows": [135], "LLM": [137], "directly": [139], "produce": [140], "results": [142, 208], "represented": [143], "as": [144], "polygons,": [145], "propose": [147, 181], "region-attribute": [149], "corresponding": [150], "table": [151], "simulate": [153], "human": [155], "visual": [156], "system": [157], "provide": [159], "multi-modal": [160], "guidance.": [161], "We": [162], "also": [163], "synthesize": [164], "pseudo": [165], "use": [168], "curriculum": [169], "learning": [170], "pretraining": [172], "augment": [174], "data": [175], "better": [178], "optimization,": [179], "novel": [183], "inference": [184], "method": [185], "mitigate": [187], "potential": [188, 223], "oversegmentation": [189], "hallucinations": [190], "caused": [191], "regional": [194], "guidance": [195], "information.": [196], "Incorporating": [197], "these": [198], "designs,": [199], "constitutes": [201], "effective": [203], "state-of-the-art": [207], "multiple": [210], "datasets": [211], "including": [212], "PASCAL-$5^{i}$5i,": [213], "COCO-$20^{i}$20i,": [214], "FSS-1000.": [216], "Our": [217], "performance": [219], "showcases": [220], "remarkable": [222], "applying": [225], "process": [228], "vision": [230], "tasks.": [231]}, "primary_topic": {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9800000190734863, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9800000190734863, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.014700000174343586, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.003599999938160181, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1109/tpami.2025.3573609", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tpami.2025.3573609", "pdf_url": null, "source": {"id": "https://openalex.org/S199944782", "display_name": "IEEE Transactions on Pattern Analysis and Machine Intelligence", "issn_l": "0162-8828", "issn": ["0162-8828", "1939-3539", "2160-9292"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-3", "medline", "norway-2"], "host_organization": "https://openalex.org/P4310320439", "host_organization_name": "IEEE Computer Society", "host_organization_lineage": ["https://openalex.org/P4310320439", "https://openalex.org/P4310319808"], "host_organization_lineage_names": ["IEEE Computer Society", "Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Transactions on Pattern Analysis and Machine Intelligence", "raw_type": "journal-article"}, "cited_by_count": 6, "is_retracted": false}, {"id": "https://openalex.org/W4407764019", "doi": "https://doi.org/10.48550/arxiv.2502.13179", "title": "PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models", "publication_year": 2025, "publication_date": "2025-02-18", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5005368623", "display_name": "Jiaqi Zhao", "orcid": "https://orcid.org/0009-0008-4325-9422", "observed_orcids": ["https://orcid.org/0009-0008-4325-9422"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Jiaqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhang, Miao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Miao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100432583", "display_name": "Ming Wang", "orcid": "https://orcid.org/0000-0003-0976-9871", "observed_orcids": ["https://orcid.org/0000-0003-0976-9871"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Ming", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5090850708", "display_name": "Yuzhang Shang", "orcid": "https://orcid.org/0000-0003-2286-6668", "observed_orcids": ["https://orcid.org/0000-0003-2286-6668"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shang, Yuzhang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103144603", "display_name": "Kaihao Zhang", "orcid": "https://orcid.org/0000-0002-4317-660X", "observed_orcids": ["https://orcid.org/0000-0002-4317-660X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Kaihao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5075938343", "display_name": "Weili Guan", "orcid": "https://orcid.org/0000-0002-5658-5509", "observed_orcids": ["https://orcid.org/0000-0002-5658-5509"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Guan, Weili", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100631216", "display_name": "Yaowei Wang", "orcid": "https://orcid.org/0000-0003-2197-9038", "observed_orcids": ["https://orcid.org/0000-0003-2197-9038", "https://orcid.org/0009-0001-4531-1414"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yaowei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Zhang, Min", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Min", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "suffer": [4], "severe": [5], "performance": [6, 184], "degradation": [7], "when": [8], "facing": [9], "extremely": [10, 58, 174, 186], "low-bit": [11, 59, 175, 187], "(sub": [12], "2-bit)": [13], "quantization.": [14, 188], "Several": [15], "existing": [16], "sub": [17], "2-bit": [18], "post-training": [19], "quantization": [20, 67, 101, 143, 152, 167], "(PTQ)": [21], "methods": [22], "utilize": [23], "a": [24, 78, 148], "mix-precision": [25], "scheme": [26], "by": [27], "leveraging": [28], "an": [29, 41, 57, 115], "unstructured": [30], "fine-grained": [31], "mask": [32, 81], "to": [33, 68, 103, 109, 125], "explicitly": [34], "distinguish": [35], "salient": [36, 106], "weights,": [37], "while": [38], "which": [39, 64], "introduces": [40], "extra": [42], "1-bit": [43], "or": [44], "more": [45], "per": [46, 86], "weight.": [47], "To": [48], "explore": [49], "the": [50, 71, 93, 97, 159, 163, 170], "real": [51], "limit": [52], "of": [53, 95, 100, 162], "PTQ,": [54], "we": [55, 75, 145, 155], "propose": [56, 147], "PTQ": [60], "method": [61], "called": [62, 151], "PTQ1.61,": [63], "enables": [65], "weight": [66, 87, 107, 160], "1.61-bit": [69], "for": [70], "first": [72, 76], "time.": [73], "Specifically,": [74], "introduce": [77], "one-dimensional": [79], "structured": [80], "with": [82], "negligibly": [83], "additional": [84], "0.0002-bit": [85], "based": [88], "on": [89, 141], "input": [90], "activations": [91], "from": [92, 136], "perspective": [94], "reducing": [96], "upper": [98], "bound": [99], "error": [102], "allocate": [104], "corresponding": [105], "channels": [108, 113], "4-bit.": [110], "For": [111], "non-salient": [112], "binarization,": [114], "efficient": [116], "block-wise": [117], "scaling": [118], "factors": [119], "optimization": [120], "framework": [121], "is": [122], "then": [123], "presented": [124], "take": [126], "implicit": [127], "row-wise": [128], "correlations": [129], "and": [130], "angular": [131], "biases": [132], "into": [133], "account.": [134], "Different": [135], "prior": [137], "works": [138], "that": [139, 157], "concentrate": [140], "adjusting": [142], "methodologies,": [144], "further": [146], "novel": [149], "paradigm": [150], "preprocessing,": [153], "where": [154], "argue": [156], "transforming": [158], "distribution": [161], "pretrained": [164], "model": [165], "before": [166], "can": [168], "alleviate": [169], "difficulty": [171], "in": [172, 185], "per-channel": [173], "PTQ.": [176], "Extensive": [177], "experiments": [178], "indicate": [179], "our": [180], "PTQ1.61": [181], "achieves": [182], "state-of-the-art": [183], "Codes": [189], "are": [190], "available": [191], "at": [192], "https://github.com/zjq0455/PTQ1.61.": [193]}, "primary_topic": {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.9833999872207642, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.9833999872207642, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.0020000000949949026, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10363", "display_name": "Low-power high-performance VLSI design", "score": 0.00139999995008111, "subfield": {"id": "https://openalex.org/subfields/2208", "display_name": "Electrical and Electronic Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.13179", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.13179", "pdf_url": "https://arxiv.org/pdf/2502.13179", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406733371", "doi": "https://doi.org/10.48550/arxiv.2501.11770", "title": "The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers", "publication_year": 2025, "publication_date": "2025-01-20", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5004973139", "display_name": "Alina Starovolsky-Shitrit", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I16391192", "display_name": "Tel Aviv University", "ror": "https://ror.org/04mhzgx49", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I16391192"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Starovolsky-Shitrit, Alina", "raw_affiliation_strings": ["Tel-Aviv University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tel-Aviv University", "institution_ids": ["https://openalex.org/I16391192"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115996843", "display_name": "Alon Neduva", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I124227911", "display_name": "Ben-Gurion University of the Negev", "ror": "https://ror.org/05tkyf982", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I124227911"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Neduva, Alon", "raw_affiliation_strings": ["Ben-Gurion University of the Negev"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Ben-Gurion University of the Negev", "institution_ids": ["https://openalex.org/I124227911"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115996844", "display_name": "Naama Appel Doron", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I16391192", "display_name": "Tel Aviv University", "ror": "https://ror.org/04mhzgx49", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I16391192"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Doron, Naama Appel", "raw_affiliation_strings": ["Tel-Aviv University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tel-Aviv University", "institution_ids": ["https://openalex.org/I16391192"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Gafni, Itamar", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gafni, Itamar", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Daniel, Ella", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I16391192", "display_name": "Tel Aviv University", "ror": "https://ror.org/04mhzgx49", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I16391192"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Daniel, Ella", "raw_affiliation_strings": ["Tel-Aviv University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tel-Aviv University", "institution_ids": ["https://openalex.org/I16391192"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5011919726", "display_name": "Oren Tsur", "orcid": "https://orcid.org/0000-0002-6809-2234", "observed_orcids": ["https://orcid.org/0000-0002-6809-2234"]}, "institutions": [{"id": "https://openalex.org/I124227911", "display_name": "Ben-Gurion University of the Negev", "ror": "https://ror.org/05tkyf982", "country_code": "IL", "type": "education", "lineage": ["https://openalex.org/I124227911"]}], "countries": ["IL"], "is_corresponding": false, "raw_author_name": "Tsur, Oren", "raw_affiliation_strings": ["Ben-Gurion University of the Negev"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Ben-Gurion University of the Negev", "institution_ids": ["https://openalex.org/I124227911"]}]}], "abstract_inverted_index": {"Societal": [0], "and": [1, 11, 15, 45, 71, 82, 121, 134, 155, 190, 192, 237], "personal": [2], "values": [3, 18, 61, 118, 135, 203, 233], "are": [4, 128, 136], "transmitted": [5], "to": [6, 86, 131, 231, 248], "younger": [7], "generations": [8], "through": [9, 32, 49], "interaction": [10], "exposure.": [12], "Traditionally,": [13], "children": [14, 70], "adolescents": [16], "learned": [17], "from": [19, 62, 119, 138, 234], "parents,": [20], "educators,": [21], "or": [22, 205], "peers.": [23], "Nowadays,": [24], "social": [25, 239, 256], "platforms": [26], "serve": [27], "as": [28, 39], "a": [29, 75, 122, 158, 162, 173], "significant": [30], "channel": [31], "which": [33, 50, 126], "youth": [34], "(and": [35], "adults)": [36], "consume": [37], "information,": [38], "the": [40, 47, 87, 139, 145, 152, 170, 179, 185, 194, 197, 208, 213, 221, 228, 246], "main": [41], "medium": [42, 48], "of": [43, 77, 79, 92, 101, 117, 161, 172, 187, 196, 202, 217, 223], "entertainment,": [44], "possibly": [46], "they": [51], "learn": [52], "different": [53, 198], "values.": [54], "In": [55], "this": [56, 226], "paper": [57], "we": [58, 111, 211], "extract": [59, 232], "implicit": [60], "TikTok": [63, 80, 218, 235], "movies": [64, 81], "uploaded": [65], "by": [66], "online": [67], "influencers": [68], "targeting": [69], "adolescents.": [72], "We": [73, 95, 142, 182], "curated": [74], "dataset": [76, 216], "hundreds": [78], "annotated": [83], "them": [84], "according": [85], "well": [88], "established": [89], "Schwartz": [90], "Theory": [91], "Personal": [93], "Values.": [94], "then": [96], "experimented": [97], "with": [98], "an": [99], "array": [100], "language": [102], "models,": [103], "investigating": [104], "their": [105], "utility": [106], "in": [107, 125, 166, 178, 207, 241, 254], "value": [108, 252], "identification.": [109], "Specifically,": [110], "considered": [112], "two": [113], "pipelines:": [114], "direct": [115, 153], "extraction": [116], "video": [120], "2-step": [123, 146], "approach": [124, 147, 154], "videos": [127], "first": [129, 214, 229], "converted": [130], "elaborated": [132], "scripts": [133], "extracted": [137], "textual": [140], "scripts.": [141], "find": [143], "that": [144, 156], "performs": [148], "significantly": [149], "better": [150], "than": [151], "using": [157], "few-shot": [159], "application": [160], "Large": [163], "Language": [164, 176], "Model": [165, 177], "both": [167], "stages": [168], "outperformed": [169], "use": [171], "fine-tuned": [174], "Masked": [175], "second": [180], "stage.": [181], "further": [183], "discuss": [184], "impact": [186], "continuous": [188], "pretraining": [189], "fine-tuning": [191], "compare": [193], "performance": [195], "models": [199], "on": [200, 251], "identification": [201], "endorsed": [204], "confronted": [206], "TikTok.": [209], "Finally,": [210], "share": [212], "values-annotated": [215], "videos.": [219], "To": [220], "best": [222], "our": [224], "knowledge,": [225], "is": [227], "attempt": [230], "specifically,": [236], "visual": [238], "media": [240], "general.": [242], "Our": [243], "results": [244], "pave": [245], "way": [247], "future": [249], "research": [250], "transmission": [253], "video-based": [255], "platforms.": [257]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.6449999809265137, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.6449999809265137, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12531", "display_name": "Values and Moral Education", "score": 0.10970000177621841, "subfield": {"id": "https://openalex.org/subfields/3304", "display_name": "Education"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T12262", "display_name": "Hate Speech and Cyberbullying Detection", "score": 0.08479999750852585, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2501.11770", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2501.11770", "pdf_url": "https://arxiv.org/pdf/2501.11770", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7117572120", "doi": "https://doi.org/10.48550/arxiv.2512.21675", "title": "UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture", "publication_year": 2025, "publication_date": "2025-12-25", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5121555533", "display_name": "Shuo Cao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cao, Shuo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100769532", "display_name": "Jiayang Li", "orcid": "https://orcid.org/0000-0001-9271-3988", "observed_orcids": ["https://orcid.org/0000-0001-9271-3988"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Jiayang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039464470", "display_name": "Xiaohui Li", "orcid": "https://orcid.org/0000-0003-0776-265X", "observed_orcids": ["https://orcid.org/0000-0003-0776-265X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xiaohui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113380881", "display_name": "Yuandong Pu", "orcid": "https://orcid.org/0000-0003-3764-0370", "observed_orcids": ["https://orcid.org/0000-0003-3764-0370"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pu, Yuandong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5127848808", "display_name": "Kaiwen Zhu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhu, Kaiwen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5074618663", "display_name": "Yuan Gao", "orcid": "https://orcid.org/0000-0001-7007-9605", "observed_orcids": ["https://orcid.org/0000-0001-7007-9605"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gao, Yuanting", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121149752", "display_name": "Siqi Luo", "orcid": "https://orcid.org/0009-0006-5369-2321", "observed_orcids": ["https://orcid.org/0009-0006-5369-2321"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Siqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5125478781", "display_name": "Yi Xin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xin, Yi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5126133011", "display_name": "Qi Qin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qin, Qi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121584145", "display_name": "Yu Zhou", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhou, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107672073", "display_name": "Xiangyu Chen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Xiangyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121542075", "display_name": "Wenlong Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Wenlong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121234725", "display_name": "Bin Fu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fu, Bin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5127892833", "display_name": "Yu Qiao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qiao, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5107946409", "display_name": "Yihao Liu", "orcid": "https://orcid.org/0000-0003-3187-9903", "observed_orcids": ["https://orcid.org/0000-0003-3187-9903", "https://orcid.org/0009-0009-0517-3334"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yihao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Multimodal": [0], "large": [1], "language": [2], "models": [3], "(MLLMs)": [4], "have": [5], "achieved": [6], "remarkable": [7], "progress": [8], "in": [9, 123], "visual": [10, 15], "understanding": [11, 42, 105], "tasks": [12], "such": [13], "as": [14, 109], "grounding,": [16], "segmentation,": [17], "and": [18, 50, 58, 81, 92, 106], "captioning.": [19], "However,": [20], "their": [21], "ability": [22], "to": [23, 62], "perceive": [24], "perceptual-level": [25, 40, 64, 103, 147], "image": [26, 41, 65, 104, 149], "features": [27], "remains": [28], "limited.": [29], "In": [30], "this": [31, 69], "work,": [32], "we": [33, 71], "present": [34], "UniPercept-Bench,": [35], "a": [36, 54, 73, 110, 133, 138, 142], "unified": [37], "framework": [38], "for": [39, 114, 145], "across": [43, 87], "three": [44], "key": [45], "domains:": [46], "Aesthetics,": [47], "Quality,": [48], "Structure": [49], "Texture.": [51], "We": [52], "establish": [53], "hierarchical": [55], "definition": [56], "system": [57], "construct": [59], "large-scale": [60], "datasets": [61], "evaluate": [63], "understanding.": [66, 150], "Based": [67], "on": [68, 102], "foundation,": [70], "develop": [72], "strong": [74, 139], "baseline": [75], "UniPercept": [76, 98], "trained": [77], "via": [78], "Domain-Adaptive": [79], "Pre-Training": [80], "Task-Aligned": [82], "RL,": [83], "enabling": [84], "robust": [85], "generalization": [86], "both": [88], "Visual": [89, 93], "Rating": [90], "(VR)": [91], "Question": [94], "Answering": [95], "(VQA)": [96], "tasks.": [97], "outperforms": [99], "existing": [100], "MLLMs": [101, 127], "can": [107], "serve": [108], "plug-and-play": [111], "reward": [112], "model": [113], "text-to-image": [115], "generation.": [116], "This": [117], "work": [118], "defines": [119], "Perceptual-Level": [120], "Image": [121], "Understanding": [122], "the": [124, 130], "era": [125], "of": [126, 132], "and,": [128], "through": [129], "introduction": [131], "comprehensive": [134], "benchmark": [135], "together": [136], "with": [137], "baseline,": [140], "provides": [141], "solid": [143], "foundation": [144], "advancing": [146], "multimodal": [148]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2512.21675", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.21675", "pdf_url": "https://arxiv.org/pdf/2512.21675", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411639796", "doi": "https://doi.org/10.1109/mnet.2025.3583088", "title": "Large Language Models Powered Malicious Traffic Detection: Architecture, Opportunities, and Case Study", "publication_year": 2025, "publication_date": "2025-06-25", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5080142175", "display_name": "Xinggong Zhang", "orcid": "https://orcid.org/0000-0003-0484-5951", "observed_orcids": ["https://orcid.org/0000-0003-0484-5951"]}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xinggong Zhang", "raw_affiliation_strings": ["Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "Peking University, China"], "raw_orcid": "https://orcid.org/0000-0003-0484-5951", "affiliations": [{"raw_affiliation_string": "Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}, {"raw_affiliation_string": "Peking University, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113898228", "display_name": "Haotian Meng", "orcid": "https://orcid.org/0009-0006-7739-8469", "observed_orcids": ["https://orcid.org/0009-0006-7739-8469"]}, "institutions": [{"id": "https://openalex.org/I6507939", "display_name": "China United Network Communications Group (China)", "ror": "https://ror.org/028w99c90", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I6507939"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Haotian Meng", "raw_affiliation_strings": ["China Unicom, Beijing, China", "China Unicom, China"], "raw_orcid": "https://orcid.org/0009-0006-7739-8469", "affiliations": [{"raw_affiliation_string": "China Unicom, Beijing, China", "institution_ids": ["https://openalex.org/I6507939"]}, {"raw_affiliation_string": "China Unicom, China", "institution_ids": ["https://openalex.org/I6507939"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Qingyang Li", "orcid": "https://orcid.org/0009-0009-0552-865X", "observed_orcids": ["https://orcid.org/0009-0009-0552-865X"]}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Qingyang Li", "raw_affiliation_strings": ["Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "Peking University, China"], "raw_orcid": "https://orcid.org/0009-0009-0552-865X", "affiliations": [{"raw_affiliation_string": "Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}, {"raw_affiliation_string": "Peking University, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5043915518", "display_name": "Y. P. Tan", "orcid": "https://orcid.org/0009-0002-8883-9865", "observed_orcids": ["https://orcid.org/0009-0002-8883-9865"]}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yunpeng Tan", "raw_affiliation_strings": ["Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "Peking University, China"], "raw_orcid": "https://orcid.org/0009-0002-8883-9865", "affiliations": [{"raw_affiliation_string": "Wangxuan Institute of Computer Technology, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570"]}, {"raw_affiliation_string": "Peking University, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Lei Zhang", "orcid": "https://orcid.org/0000-0001-7991-2915", "observed_orcids": ["https://orcid.org/0000-0001-7991-2915"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lei Zhang", "raw_affiliation_strings": ["Zhongguancun Laboratory, Beijing, China", "Zhongguancun Lab, China"], "raw_orcid": "https://orcid.org/0000-0001-7991-2915", "affiliations": [{"raw_affiliation_string": "Zhongguancun Laboratory, Beijing, China", "institution_ids": []}, {"raw_affiliation_string": "Zhongguancun Lab, China", "institution_ids": []}]}], "abstract_inverted_index": {"Malicious": [0], "traffic": [1, 14, 77, 103, 116, 144], "detection": [2, 167, 177], "is": [3], "a": [4, 26, 44, 68, 107, 169, 195], "pivotal": [5], "technology": [6], "for": [7, 47, 76], "network": [8, 13, 17, 48], "security": [9], "to": [10, 200], "identify": [11, 136], "abnormal": [12], "and": [15, 37, 84, 124, 131, 155], "detect": [16], "attacks.": [18], "Large": [19, 97], "Language": [20, 98], "Models": [21, 99], "(LLMs)": [22, 100], "are": [23, 157], "trained": [24], "on": [25, 61, 73, 91, 164, 178], "vast": [27], "corpus": [28], "of": [29, 35, 59, 70, 96, 110, 113, 121, 133, 149], "text,": [30], "have": [31, 52], "amassed": [32], "remarkable": [33], "capabilities": [34, 132, 185], "context-understanding": [36], "commonsense": [38], "knowledge.": [39], "This": [40], "has": [41], "opened": [42], "up": [43], "new": [45], "door": [46], "attacks": [49], "detection.": [50, 104], "Researchers": [51], "already": [53], "initiated": [54], "discussions": [55], "regarding": [56], "the": [57, 82, 93, 111, 119, 129, 151], "application": [58], "LLMs": [60, 75], "specific": [62], "cyber-security": [63], "tasks.": [64], "Unfortunately,": [65], "there": [66], "remains": [67], "lack": [69], "comprehensive": [71], "analysis": [72], "harnessing": [74], "detection,": [78, 117], "as": [79, 81, 168], "well": [80], "opportunities": [83, 154], "challenges.": [85], "In": [86], "this": [87], "paper,": [88], "we": [89, 135, 160], "focus": [90], "unleashing": [92], "full": [94], "potential": [95], "in": [101, 143, 186], "malicious": [102, 115], "We": [105], "present": [106, 161], "holistic": [108], "view": [109], "architecture": [112], "LLM-powered": [114, 165], "including": [118], "procedures": [120], "Pre-training,": [122], "Fine-tuning,": [123], "Detection.": [125], "Especially,": [126], "by": [127, 182], "exploring": [128], "knowledge": [130], "LLM,": [134], "three": [137], "distinct": [138], "roles": [139], "LLM": [140], "can": [141], "act": [142], "classification:Classifier,Encoder,": [145], "andPredictor.": [146], "For": [147], "each": [148], "them,": [150], "modeling": [152], "paradigm,": [153], "challenges": [156], "elaborated.": [158], "Finally,": [159], "our": [162], "design": [163], "DDoS": [166, 181], "case": [170], "study.": [171], "The": [172, 189], "proposed": [173], "framework": [174], "attains": [175], "accurate": [176], "carpet": [179], "bombing": [180], "exploiting": [183], "LLMs\u2019": [184], "contextual": [187], "mining.": [188], "evaluation": [190], "shows": [191], "its": [192], "efficacy,": [193], "exhibiting": [194], "nearly": [196], "35%": [197], "improvement": [198], "compared": [199], "existing": [201], "systems.": [202]}, "primary_topic": {"id": "https://openalex.org/T10400", "display_name": "Network Security and Intrusion Detection", "score": 0.9916999936103821, "subfield": {"id": "https://openalex.org/subfields/1705", "display_name": "Computer Networks and Communications"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10400", "display_name": "Network Security and Intrusion Detection", "score": 0.9916999936103821, "subfield": {"id": "https://openalex.org/subfields/1705", "display_name": "Computer Networks and Communications"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11598", "display_name": "Internet Traffic Analysis and Secure E-voting", "score": 0.005200000014156103, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 0.0013000000035390258, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1109/mnet.2025.3583088", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/mnet.2025.3583088", "pdf_url": null, "source": {"id": "https://openalex.org/S186584794", "display_name": "IEEE Network", "issn_l": "0890-8044", "issn": ["0890-8044", "1558-156X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-3", "norway-1"], "host_organization": "https://openalex.org/P4310319808", "host_organization_name": "Institute of Electrical and Electronics Engineers", "host_organization_lineage": ["https://openalex.org/P4310319808"], "host_organization_lineage_names": ["Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Network", "raw_type": "journal-article"}, "cited_by_count": 8, "is_retracted": false}, {"id": "https://openalex.org/W7126175111", "doi": "https://doi.org/10.18280/isi.301215", "title": "LLM-Cardio: A Large Language Model-Based Assistant for Cardiovascular Health Inquiry and Diagnostic Support Using Wearable Data", "publication_year": 2025, "publication_date": "2025-12-31", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5082972248", "display_name": "Sabrina Mehdi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sabrina Mehdi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5081167604", "display_name": "Sofia Kouah", "orcid": "https://orcid.org/0000-0002-1538-5543", "observed_orcids": ["https://orcid.org/0000-0002-1538-5543"]}, "institutions": [{"id": "https://openalex.org/I3132180716", "display_name": "Larbi Ben M'hidi University of Oum El Bouaghi", "ror": "https://ror.org/0034tbg85", "country_code": "DZ", "type": "education", "lineage": ["https://openalex.org/I3132180716"]}], "countries": ["DZ"], "is_corresponding": false, "raw_author_name": "Sofia Kouah", "raw_affiliation_strings": ["Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}, {"raw_affiliation_string": "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007627975", "display_name": "Asma Saighi", "orcid": "https://orcid.org/0000-0003-3790-2262", "observed_orcids": ["https://orcid.org/0000-0003-3790-2262"]}, "institutions": [{"id": "https://openalex.org/I3132180716", "display_name": "Larbi Ben M'hidi University of Oum El Bouaghi", "ror": "https://ror.org/0034tbg85", "country_code": "DZ", "type": "education", "lineage": ["https://openalex.org/I3132180716"]}], "countries": ["DZ"], "is_corresponding": false, "raw_author_name": "Asma Saighi", "raw_affiliation_strings": ["Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}, {"raw_affiliation_string": "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5072472908", "display_name": "Soumia Zertal", "orcid": "https://orcid.org/0000-0003-0127-900X", "observed_orcids": ["https://orcid.org/0000-0003-0127-900X"]}, "institutions": [{"id": "https://openalex.org/I3132180716", "display_name": "Larbi Ben M'hidi University of Oum El Bouaghi", "ror": "https://ror.org/0034tbg85", "country_code": "DZ", "type": "education", "lineage": ["https://openalex.org/I3132180716"]}], "countries": ["DZ"], "is_corresponding": false, "raw_author_name": "Soumia Zertal", "raw_affiliation_strings": ["Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Artificial Intelligence and Autonomous Things Laboratory (IAOA) , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}, {"raw_affiliation_string": "Department of Mathematics and Computer Sciences , University of Oum El Bouaghi , Oum El Bouaghi 04000 , Algeria", "institution_ids": ["https://openalex.org/I3132180716"]}]}], "abstract_inverted_index": {"The": [0], "global": [1], "increase": [2], "in": [3, 94, 161], "cardiovascular": [4, 55, 104, 199], "disease": [5], "(CVD)": [6], "cases,": [7, 83, 123], "along": [8], "with": [9, 47, 97, 175, 191], "the": [10, 61, 66, 110, 152, 169, 186], "growing": [11], "use": [12], "of": [13, 31, 112, 171], "wearable": [14, 43, 173], "health": [15], "technologies,": [16], "has": [17], "created": [18], "a": [19, 72, 113, 147], "demand": [20], "for": [21, 53, 178, 188], "intelligent": [22, 179], "tools": [23], "that": [24, 41, 75], "support": [25, 28], "early": [26], "diagnostic": [27, 80, 105, 120], "and": [29, 44, 84, 124, 135, 182, 184, 194], "monitoring": [30, 143, 181], "heart": [32], "conditions.This": [33], "work": [34], "introduces": [35], "LLM-Cardio,": [36], "an": [37, 98], "AI-driven": [38], "cardiology": [39], "assistant": [40], "combines": [42], "clinical": [45, 82, 122, 195], "data": [46, 92], "large": [48], "language": [49], "model": [50, 154], "(LLM)": [51], "reasoning": [52, 177], "personalized": [54], "assessment.The": [56], "system": [57, 88], "is": [58, 109], "powered": [59], "by": [60], "Meta-Llama-3.1-8B-Instructmodel": [62], "(4-bit),": [63], "fine-tuned": [64, 153], "using": [65], "LoRA": [67], "(Low-Rank": [68], "Adaptation)": [69], "method": [70], "on": [71, 116, 164], "cardiology-specific": [73, 117], "dataset": [74], "includes": [76], "structured": [77], "medical": [78, 85, 125], "records,": [79], "reports,": [81, 121], "Q&A": [86, 126], "data.The": [87], "integrates": [89], "streaming": [90], "vital-sign": [91], "(simulated": [93], "this": [95], "study)": [96], "instruction-tuned": [99], "LLM": [100, 115], "to": [101], "deliver": [102], "adaptive": [103], "support.A": [106], "key": [107], "contribution": [108], "fine-tuning": [111], "pretrained": [114], "datasets,": [118], "including": [119], "data.Users": [127], "can": [128], "describe": [129], "symptoms": [130], "or": [131], "ask": [132], "cardiology-related": [133], "questions": [134], "receive": [136], "medically": [137], "grounded,": [138], "explainable": [139], "responses,": [140], "while": [141], "simultaneously": [142], "vital": [144], "signs": [145], "through": [146], "responsive": [148], "mobile": [149], "interface.Using": [150], "BERTScore,": [151], "achieved": [155], "Precision=0.9463,Recall=0.9527,F1-score=0.9493,": [156], "outperforming": [157], "baseline": [158], "generative": [159], "models": [160], "semantic": [162], "similarity": [163], "our": [165], "test": [166], "set.LLM-Cardio": [167], "illustrates": [168], "potential": [170], "merging": [172], "technologies": [174], "AI": [176], "cardiac": [180], "diagnosis,": [183], "sets": [185], "groundwork": [187], "future": [189], "integration": [190], "real": [192], "devices": [193], "validation": [196], "toward": [197], "proactive": [198], "care.": [200]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.8008000254631042, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.8008000254631042, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11396", "display_name": "Artificial Intelligence in Healthcare", "score": 0.17790000140666962, "subfield": {"id": "https://openalex.org/subfields/3605", "display_name": "Health Information Management"}, "field": {"id": "https://openalex.org/fields/36", "display_name": "Health Professions"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.006500000134110451, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.18280/isi.301215", "is_oa": true, "landing_page_url": "https://doi.org/10.18280/isi.301215", "pdf_url": "https://www.iieta.org/download/file/fid/192156", "source": {"id": "https://openalex.org/S1757003", "display_name": "Ing\u00e9nierie des syst\u00e8mes d information", "issn_l": "1633-1311", "issn": ["1633-1311", "2116-7125"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1", "norway-1"], "host_organization": "https://openalex.org/P4310311056", "host_organization_name": "Lavoisier publishing", "host_organization_lineage": ["https://openalex.org/P4310311056"], "host_organization_lineage_names": ["Lavoisier publishing"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Ing\u00e9nierie des syst\u00e8mes d information", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411336859", "doi": "https://doi.org/10.1109/tpami.2025.3580234", "title": "Toward a Holistic Evaluation of Robustness in CLIP Models", "publication_year": 2025, "publication_date": "2025-06-16", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5049740771", "display_name": "Weijie Tu", "orcid": "https://orcid.org/0009-0002-7364-298X", "observed_orcids": ["https://orcid.org/0009-0002-7364-298X"]}, "institutions": [{"id": "https://openalex.org/I118347636", "display_name": "Australian National University", "ror": "https://ror.org/019wvm592", "country_code": "AU", "type": "education", "lineage": ["https://openalex.org/I118347636"]}], "countries": ["AU"], "is_corresponding": false, "raw_author_name": "Weijie Tu", "raw_affiliation_strings": ["School of Computing, Australian National University, Canberra, ACT, Australia", "School of Computing, The Australian National University, Canberra, ACT, Australia"], "raw_orcid": "https://orcid.org/0009-0002-7364-298X", "affiliations": [{"raw_affiliation_string": "School of Computing, Australian National University, Canberra, ACT, Australia", "institution_ids": ["https://openalex.org/I118347636"]}, {"raw_affiliation_string": "School of Computing, The Australian National University, Canberra, ACT, Australia", "institution_ids": ["https://openalex.org/I118347636"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065550142", "display_name": "Weijian Deng", "orcid": "https://orcid.org/0000-0003-1565-742X", "observed_orcids": ["https://orcid.org/0000-0003-1565-742X"]}, "institutions": [{"id": "https://openalex.org/I118347636", "display_name": "Australian National University", "ror": "https://ror.org/019wvm592", "country_code": "AU", "type": "education", "lineage": ["https://openalex.org/I118347636"]}], "countries": ["AU"], "is_corresponding": false, "raw_author_name": "Weijian Deng", "raw_affiliation_strings": ["School of Computing, Australian National University, Canberra, ACT, Australia", "School of Computing, The Australian National University, Canberra, ACT, Australia"], "raw_orcid": "https://orcid.org/0000-0003-1565-742X", "affiliations": [{"raw_affiliation_string": "School of Computing, Australian National University, Canberra, ACT, Australia", "institution_ids": ["https://openalex.org/I118347636"]}, {"raw_affiliation_string": "School of Computing, The Australian National University, Canberra, ACT, Australia", "institution_ids": ["https://openalex.org/I118347636"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5111839117", "display_name": "Tom Gedeon", "orcid": "https://orcid.org/0000-0001-8356-4909", "observed_orcids": ["https://orcid.org/0000-0001-8356-4909"]}, "institutions": [{"id": "https://openalex.org/I118347636", "display_name": "Australian National University", "ror": "https://ror.org/019wvm592", "country_code": "AU", "type": "education", "lineage": ["https://openalex.org/I118347636"]}], "countries": ["AU"], "is_corresponding": false, "raw_author_name": "Tom Gedeon", "raw_affiliation_strings": ["Australian National University, University of &#x00D3;buda, Budapest, Hungary", "Australian National University, Australia"], "raw_orcid": "https://orcid.org/0000-0001-8356-4909", "affiliations": [{"raw_affiliation_string": "Australian National University, University of &#x00D3;buda, Budapest, Hungary", "institution_ids": ["https://openalex.org/I118347636"]}, {"raw_affiliation_string": "Australian National University, Australia", "institution_ids": ["https://openalex.org/I118347636"]}]}], "abstract_inverted_index": {"Contrastive": [0], "Language-Image": [1], "Pre-training": [2], "(CLIP)": [3], "models": [4, 74, 112, 185, 207], "have": [5], "shown": [6], "significant": [7, 176], "potential,": [8], "particularly": [9], "in": [10, 48, 89, 172, 178, 218], "zero-shot": [11], "classification": [12, 23, 64, 127, 219], "across": [13], "diverse": [14], "distribution": [15], "shifts.": [16], "Building": [17], "on": [18, 122, 139, 204], "existing": [19], "evaluations": [20], "of": [21, 34, 136, 168, 241], "overall": [22], "robustness,": [24], "this": [25, 124, 197], "work": [26], "aims": [27], "to": [28, 46, 86, 187, 200, 231], "provide": [29], "a": [30, 175, 189], "more": [31], "comprehensive": [32], "assessment": [33], "CLIP": [35, 73, 90, 116, 140, 173, 184, 212, 225, 242], "by": [36], "introducing": [37], "several": [38, 158], "new": [39], "perspectives.": [40], "First,": [41], "we": [42, 53, 67, 82, 99, 132], "investigate": [43], "their": [44, 179], "robustness": [45, 180, 238], "variations": [47], "specific": [49], "visual": [50, 119, 170], "factors.": [51], "Second,": [52], "assess": [54], "two": [55], "critical": [56], "safety": [57], "objectives-confidence": [58], "uncertainty": [59], "and": [60, 78, 105, 152, 239], "out-of-distribution": [61], "detection-beyond": [62], "mere": [63], "accuracy.": [65], "Third,": [66], "evaluate": [68], "the": [69, 76, 101, 118, 134, 166, 169, 211, 237], "finesse": [70], "with": [71], "which": [72], "bridge": [75], "image": [77, 96], "text": [79], "modalities.": [80], "Fourth,": [81], "extend": [83], "our": [84], "examination": [85], "3D": [87, 182], "awareness": [88], "models,": [91], "moving": [92], "beyond": [93], "traditional": [94], "2D": [95], "understanding.": [97], "Finally,": [98], "explore": [100], "interaction": [102, 125], "between": [103], "vision": [104, 213], "language": [106], "encoders": [107], "within": [108], "modern": [109], "large": [110], "multimodal": [111], "(LMMs)": [113], "that": [114], "utilize": [115], "as": [117], "backbone,": [120], "focusing": [121], "how": [123], "impacts": [126], "robustness.": [128], "In": [129], "each": [130], "aspect,": [131], "consider": [133], "impact": [135], "six": [137], "factors": [138], "models:": [141], "model": [142], "architecture,": [143], "training": [144, 146], "distribution,": [145], "set": [147], "size,": [148], "fine-tuning,": [149], "contrastive": [150], "loss,": [151], "test-time": [153], "prompts.": [154], "Our": [155, 227], "study": [156], "uncovers": [157], "previously": [159], "unknown": [160], "insights": [161], "into": [162], "CLIP.": [163], "For": [164], "instance,": [165], "architecture": [167], "encoder": [171], "plays": [174], "role": [177], "against": [181], "corruption.": [183], "tend": [186], "exhibit": [188, 216], "bias": [190, 198], "towards": [191], "shape": [192], "when": [193], "making": [194], "predictions.": [195], "Moreover,": [196], "tends": [199], "diminish": [201], "after": [202], "fine-tuning": [203], "ImageNet.": [205], "Vision-language": [206], "like": [208], "LLaVA,": [209], "leveraging": [210], "encoder,": [214], "could": [215], "benefits": [217], "performance": [220], "for": [221, 235], "challenging": [222], "categories": [223], "over": [224], "alone.": [226], "findings": [228], "are": [229], "poised": [230], "offer": [232], "valuable": [233], "guidance": [234], "enhancing": [236], "reliability": [240], "models.": [243]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9916999936103821, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9916999936103821, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.004399999976158142, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.002300000051036477, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1109/tpami.2025.3580234", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tpami.2025.3580234", "pdf_url": null, "source": {"id": "https://openalex.org/S199944782", "display_name": "IEEE Transactions on Pattern Analysis and Machine Intelligence", "issn_l": "0162-8828", "issn": ["0162-8828", "1939-3539", "2160-9292"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-3", "medline", "norway-2"], "host_organization": "https://openalex.org/P4310320439", "host_organization_name": "IEEE Computer Society", "host_organization_lineage": ["https://openalex.org/P4310320439", "https://openalex.org/P4310319808"], "host_organization_lineage_names": ["IEEE Computer Society", "Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Transactions on Pattern Analysis and Machine Intelligence", "raw_type": "journal-article"}, "cited_by_count": 10, "is_retracted": false}, {"id": "https://openalex.org/W4415280674", "doi": "https://doi.org/10.48550/arxiv.2510.08608", "title": "MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation", "publication_year": 2025, "publication_date": "2025-10-07", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113059708", "display_name": "Weihua Zheng", "orcid": "https://orcid.org/0009-0008-5251-5467", "observed_orcids": ["https://orcid.org/0009-0008-5251-5467"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zheng, Weihua", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003055263", "display_name": "Zhengyuan Liu", "orcid": "https://orcid.org/0009-0003-8897-4140", "observed_orcids": ["https://orcid.org/0009-0003-8897-4140"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Zhengyuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5046521217", "display_name": "Tanmoy Chakraborty", "orcid": "https://orcid.org/0000-0002-0210-0369", "observed_orcids": ["https://orcid.org/0000-0002-0210-0369"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chakraborty, Tanmoy", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100585032", "display_name": "Weiwen Xu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Weiwen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101856962", "display_name": "Xiaoxue Gao", "orcid": "https://orcid.org/0000-0003-1920-5228", "observed_orcids": ["https://orcid.org/0000-0003-1920-5228"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gao, Xiaoxue", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Tan, Bryan Chen Zhengyu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tan, Bryan Chen Zhengyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076654908", "display_name": "Bowei Zou", "orcid": "https://orcid.org/0000-0002-9624-0759", "observed_orcids": ["https://orcid.org/0000-0002-9624-0759"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zou, Bowei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100353261", "display_name": "Chang Liu", "orcid": "https://orcid.org/0000-0002-5511-6858", "observed_orcids": ["https://orcid.org/0000-0002-5511-6858"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Chang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101956873", "display_name": "Yujia Hu", "orcid": "https://orcid.org/0009-0002-7306-3144", "observed_orcids": ["https://orcid.org/0009-0002-7306-3144"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hu, Yujia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044651577", "display_name": "Xing Xie", "orcid": "https://orcid.org/0000-0002-8608-8482", "observed_orcids": ["https://orcid.org/0000-0002-8608-8482", "https://orcid.org/0000-0001-5139-4634", "https://orcid.org/0000-0001-7615-9673"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xie, Xing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040961637", "display_name": "Xiaoyuan Yi", "orcid": "https://orcid.org/0000-0003-2710-1613", "observed_orcids": ["https://orcid.org/0000-0003-2710-1613"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yi, Xiaoyuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Yao, Jing", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yao, Jing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003237783", "display_name": "Chaojun Wang", "orcid": "https://orcid.org/0000-0002-1632-1728", "observed_orcids": ["https://orcid.org/0000-0002-1632-1728", "https://orcid.org/0000-0003-3282-375X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Chaojun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100408811", "display_name": "Long Li", "orcid": "https://orcid.org/0009-0008-5898-8628", "observed_orcids": ["https://orcid.org/0009-0008-5898-8628"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Long", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103227545", "display_name": "Rui Liu", "orcid": "https://orcid.org/0009-0005-3136-3853", "observed_orcids": ["https://orcid.org/0009-0005-3136-3853", "https://orcid.org/0000-0001-5553-9095"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Rui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Liu, Huiyao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Huiyao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5058775745", "display_name": "Koji Inoue", "orcid": "https://orcid.org/0000-0002-2929-2559", "observed_orcids": ["https://orcid.org/0000-0002-2929-2559"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Inoue, Koji", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114400286", "display_name": "Ryuichi Sumida", "orcid": "https://orcid.org/0009-0005-9757-0273", "observed_orcids": ["https://orcid.org/0009-0005-9757-0273"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sumida, Ryuichi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038044080", "display_name": "Tatsuya Kawahara", "orcid": "https://orcid.org/0000-0002-2686-2296", "observed_orcids": ["https://orcid.org/0000-0002-2686-2296"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kawahara, Tatsuya", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101607448", "display_name": "Fan Xu", "orcid": "https://orcid.org/0000-0002-1358-0193", "observed_orcids": ["https://orcid.org/0000-0002-1358-0193", "https://orcid.org/0009-0005-8021-9524"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Fan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5070396778", "display_name": "Linzan Ye", "orcid": "https://orcid.org/0000-0002-7297-4432", "observed_orcids": ["https://orcid.org/0000-0002-7297-4432"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ye, Lingyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Tian, Wei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tian, Wei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100609433", "display_name": "Dong-Jun Kim", "orcid": "https://orcid.org/0000-0003-4510-2396", "observed_orcids": ["https://orcid.org/0000-0003-4510-2396"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kim, Dongjun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Jung, Jimin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jung, Jimin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014883878", "display_name": "Jaehyung Seo", "orcid": "https://orcid.org/0000-0002-4761-9818", "observed_orcids": ["https://orcid.org/0000-0002-4761-9818"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Seo, Jaehyung", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120035820", "display_name": "Nadya Yuki Wangsajaya", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wangsajaya, Nadya Yuki", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120035821", "display_name": "Pham Minh Duc", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Duc, Pham Minh", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120273631", "display_name": "Ojasva Saxena", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Saxena, Ojasva", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5093836244", "display_name": "Palash Nandi", "orcid": "https://orcid.org/0000-0002-0775-0723", "observed_orcids": ["https://orcid.org/0000-0002-0775-0723"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nandi, Palash", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Tao, Xiyan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tao, Xiyan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120035823", "display_name": "Wiwik Karlina", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Karlina, Wiwik", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Luong, Tuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luong, Tuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120035825", "display_name": "Keertana Arun Vasan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Vasan, Keertana Arun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089793938", "display_name": "Roy Ka-Wei Lee", "orcid": "https://orcid.org/0000-0002-1986-7750", "observed_orcids": ["https://orcid.org/0000-0002-1986-7750"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lee, Roy Ka-Wei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5014190404", "display_name": "Nancy F. Chen", "orcid": "https://orcid.org/0000-0003-0872-5877", "observed_orcids": ["https://orcid.org/0000-0003-0872-5877"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Nancy F.", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2, 174], "(LLMs)": [3], "are": [4], "now": [5], "used": [6], "worldwide,": [7], "yet": [8], "their": [9], "multimodal": [10, 187], "understanding": [11], "and": [12, 43, 52, 93, 129, 163, 178], "reasoning": [13, 63], "often": [14], "degrade": [15], "outside": [16], "Western,": [17], "high-resource": [18], "settings.": [19], "We": [20], "propose": [21, 107], "MMA-ASIA,": [22], "a": [23, 32, 40, 108, 137], "comprehensive": [24], "framework": [25], "to": [26], "evaluate": [27], "LLMs'": [28], "cultural": [29, 66, 126, 151], "awareness": [30], "with": [31], "focus": [33], "on": [34, 39, 103], "Asian": [35, 50], "contexts.": [36], "MMA-ASIA": [37], "centers": [38], "human-curated,": [41], "multilingual,": [42], "multimodally": [44], "aligned": [45, 80], "multiple-choice": [46], "benchmark": [47], "covering": [48], "8": [49], "countries": [51], "10": [53], "languages,": [54], "comprising": [55], "27,000": [56], "questions;": [57], "over": [58], "79": [59], "percent": [60], "require": [61], "multi-step": [62], "grounded": [64], "in": [65], "context,": [67], "moving": [68], "beyond": [69], "simple": [70], "memorization.": [71], "To": [72, 133], "our": [73], "knowledge,": [74], "this": [75, 104], "is": [76], "the": [77, 82, 149], "first": [78], "dataset": [79], "at": [81], "input": [83], "level": [84], "across": [85, 117, 176], "three": [86], "modalities:": [87], "text,": [88], "image": [89], "(visual": [90], "question": [91], "answering),": [92], "speech.": [94], "This": [95], "enables": [96], "direct": [97], "tests": [98], "of": [99], "cross-modal": [100, 123], "transfer.": [101], "Building": [102], "benchmark,": [105], "we": [106, 171], "five-dimensional": [109], "evaluation": [110], "protocol": [111], "that": [112], "measures:": [113], "(i)": [114], "cultural-awareness": [115], "disparities": [116], "countries,": [118], "(ii)": [119], "cross-lingual": [120], "consistency,": [121, 124], "(iii)": [122], "(iv)": [125], "knowledge": [127, 152], "generalization,": [128], "(v)": [130], "grounding": [131], "validity.": [132], "ensure": [134], "rigorous": [135], "assessment,": [136], "Cultural": [138], "Awareness": [139], "Grounding": [140], "Validation": [141], "Module": [142], "detects": [143], "\"shortcut": [144], "learning\"": [145], "by": [146], "checking": [147], "whether": [148], "requisite": [150], "supports": [153], "correct": [154], "answers.": [155], "Finally,": [156], "through": [157], "comparative": [158], "model": [159], "analysis,": [160], "attention": [161], "tracing,": [162], "an": [164], "innovative": [165], "Vision-ablated": [166], "Prefix": [167], "Replay": [168], "(VPR)": [169], "method,": [170], "probe": [172], "why": [173], "diverge": [175], "languages": [177], "modalities,": [179], "offering": [180], "actionable": [181], "insights": [182], "for": [183], "building": [184], "culturally": [185], "reliable": [186], "LLMs.": [188]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9955999851226807, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9955999851226807, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0031999999191612005, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2510.08608", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.08608", "pdf_url": "https://arxiv.org/pdf/2510.08608", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4414709701", "doi": "https://doi.org/10.1017/chr.2025.10013", "title": "Expanding conceptual histories: using contextualized word embeddings for the history and philosophy of the virtual particle concept", "publication_year": 2025, "publication_date": "2025-01-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5114601920", "display_name": "Michael Zichert", "orcid": "https://orcid.org/0009-0007-8575-5750", "observed_orcids": ["https://orcid.org/0009-0007-8575-5750"]}, "institutions": [{"id": "https://openalex.org/I4577782", "display_name": "Technische Universit\u00e4t Berlin", "ror": "https://ror.org/03v4gjf40", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I4577782"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Michael Zichert", "raw_affiliation_strings": ["Technische Universit\u00e4t Berlin"], "raw_orcid": "https://orcid.org/0009-0007-8575-5750", "affiliations": [{"raw_affiliation_string": "Technische Universit\u00e4t Berlin", "institution_ids": ["https://openalex.org/I4577782"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005145195", "display_name": "Arno Simons", "orcid": "https://orcid.org/0000-0003-0657-5254", "observed_orcids": ["https://orcid.org/0000-0003-0657-5254"]}, "institutions": [{"id": "https://openalex.org/I4577782", "display_name": "Technische Universit\u00e4t Berlin", "ror": "https://ror.org/03v4gjf40", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I4577782"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Arno Simons", "raw_affiliation_strings": ["Technische Universit\u00e4t Berlin"], "raw_orcid": "https://orcid.org/0000-0003-0657-5254", "affiliations": [{"raw_affiliation_string": "Technische Universit\u00e4t Berlin", "institution_ids": ["https://openalex.org/I4577782"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5007942422", "display_name": "Adrian W\u00fcthrich", "orcid": "https://orcid.org/0000-0002-6237-7327", "observed_orcids": ["https://orcid.org/0000-0002-6237-7327"]}, "institutions": [{"id": "https://openalex.org/I4577782", "display_name": "Technische Universit\u00e4t Berlin", "ror": "https://ror.org/03v4gjf40", "country_code": "DE", "type": "education", "lineage": ["https://openalex.org/I4577782"]}], "countries": ["DE"], "is_corresponding": false, "raw_author_name": "Adrian W\u00fcthrich", "raw_affiliation_strings": ["Technische Universit\u00e4t Berlin"], "raw_orcid": "https://orcid.org/0000-0002-6237-7327", "affiliations": [{"raw_affiliation_string": "Technische Universit\u00e4t Berlin", "institution_ids": ["https://openalex.org/I4577782"]}]}], "abstract_inverted_index": {"Abstract": [0], "This": [1], "article": [2], "explores": [3], "the": [4, 13, 21, 31, 42, 52, 55, 100, 105, 112, 119, 123, 126, 131, 153, 166, 173, 183], "potential": [5, 32], "of": [6, 15, 23, 33, 38, 45, 49, 54, 86, 104, 115, 125, 133, 175, 185], "large": [7], "language": [8], "models": [9], "(LLMs),": [10], "particularly": [11], "through": [12], "use": [14], "contextualized": [16], "word": [17], "embeddings,": [18], "to": [19, 29, 41, 136], "trace": [20], "evolution": [22], "scientific": [24], "concepts.": [25], "It": [26], "thus": [27], "aims": [28], "extend": [30], "LLMs,": [34], "currently": [35], "transforming": [36], "much": [37], "humanities": [39], "research,": [40], "specialized": [43], "field": [44], "history": [46], "and": [47, 102, 144, 171, 177, 182], "philosophy": [48], "science.": [50], "Using": [51], "concept": [53], "virtual": [56, 127], "particle": [57, 65, 128], "\u2013": [58, 67], "a": [59, 69, 74, 84, 157], "fundamental": [60], "idea": [61], "in": [62, 99, 152, 180], "understanding": [63], "elementary": [64], "interactions": [66], "as": [68, 165], "case": [70], "study,": [71], "we": [72, 96, 147, 161], "domain-adapted": [73], "pretrained": [75], "Bidirectional": [76], "Encoder": [77], "Representations": [78], "from": [79, 188], "Transformers": [80], "model": [81], "on": [82], "nearly": [83], "century": [85], "Physical": [87], "Review": [88], "publications.": [89], "By": [90], "employing": [91], "semantic": [92], "change": [93], "detection": [94], "techniques,": [95], "examined": [97], "shifts": [98], "meaning": [101, 114], "usage": [103], "term": [106], "\u201cvirtual.\u201d": [107], "Our": [108], "analysis": [109], "reveals": [110], "that": [111], "dominant": [113], "\u201cvirtual\u201d": [116, 134], "stabilized": [117], "after": [118], "1950s,": [120], "aligning": [121], "with": [122, 141], "formalization": [124], "concept,": [129], "while": [130], "polysemy": [132], "continued": [135], "grow.": [137], "Augmenting": [138], "these": [139], "findings": [140], "dependency": [142], "parsing": [143], "qualitative": [145], "analysis,": [146], "identify": [148], "pivotal": [149], "historical": [150, 176], "transitions": [151], "term\u2019s": [154], "usage.": [155], "In": [156], "broader": [158], "methodological": [159], "discussion,": [160], "address": [162], "challenges": [163], "such": [164], "complex": [167], "relationship": [168], "between": [169], "words": [170], "concepts,": [172], "influence": [174], "linguistic": [178], "biases": [179], "datasets,": [181], "exclusion": [184], "mathematical": [186], "formulas": [187], "text-based": [189], "approaches.": [190]}, "primary_topic": {"id": "https://openalex.org/T12377", "display_name": "Digital Humanities and Scholarship", "score": 0.9735999703407288, "subfield": {"id": "https://openalex.org/subfields/1208", "display_name": "Literature and Literary Theory"}, "field": {"id": "https://openalex.org/fields/12", "display_name": "Arts and Humanities"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T12377", "display_name": "Digital Humanities and Scholarship", "score": 0.9735999703407288, "subfield": {"id": "https://openalex.org/subfields/1208", "display_name": "Literature and Literary Theory"}, "field": {"id": "https://openalex.org/fields/12", "display_name": "Arts and Humanities"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T13910", "display_name": "Computational and Text Analysis Methods", "score": 0.020800000056624413, "subfield": {"id": "https://openalex.org/subfields/3300", "display_name": "General Social Sciences"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0010999999940395355, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1017/chr.2025.10013", "is_oa": true, "landing_page_url": "https://doi.org/10.1017/chr.2025.10013", "pdf_url": null, "source": {"id": "https://openalex.org/S5407040251", "display_name": "Computational Humanities Research", "issn_l": "2977-8158", "issn": ["2977-8158"], "is_oa": true, "is_in_doaj": true, "is_core": false, "listed_in": ["doaj", "jufo-1"], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Computational Humanities Research", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4416550811", "doi": "https://doi.org/10.48550/arxiv.2511.16652", "title": "Evolution Strategies at the Hyperscale", "publication_year": 2025, "publication_date": "2025-11-20", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Sarkar, Bidipta", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sarkar, Bidipta", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5015858529", "display_name": "Mattie Fellows", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fellows, Mattie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5095382881", "display_name": "Juan Agustin Duque", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Duque, Juan Agustin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5070313700", "display_name": "Alistair Letcher", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Letcher, Alistair", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120373806", "display_name": "Antonio Le\u00f3n Villares", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Villares, Antonio Le\u00f3n", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109684898", "display_name": "Anya Sims", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sims, Anya", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Wibault, Clarisse", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wibault, Clarisse", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Samsonov, Dmitry", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Samsonov, Dmitry", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120610267", "display_name": "Dylan Cope", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cope, Dylan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5099282523", "display_name": "Jarek Liesen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liesen, Jarek", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Li, Kang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Kang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119862166", "display_name": "Lukas Seier", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Seier, Lukas", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Wolf, Theo", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wolf, Theo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5004730335", "display_name": "Uljad Berdica", "orcid": "https://orcid.org/0000-0001-7404-9817", "observed_orcids": ["https://orcid.org/0000-0001-7404-9817"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Berdica, Uljad", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Mohl, Valentin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mohl, Valentin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103305981", "display_name": "Alexander David Goldie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Goldie, Alexander David", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5112608251", "display_name": "Aaron C. Courville", "orcid": "https://orcid.org/0000-0001-6223-0301", "observed_orcids": ["https://orcid.org/0000-0001-6223-0301"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Courville, Aaron", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049422133", "display_name": "Karin Sevegnani", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sevegnani, Karin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5056879203", "display_name": "Shimon Whiteson", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Whiteson, Shimon", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5059094093", "display_name": "Jakob Foerster", "orcid": "https://orcid.org/0000-0001-9688-2498", "observed_orcids": ["https://orcid.org/0000-0001-9688-2498"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Foerster, Jakob Nicolaus", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Evolution": [0, 48], "Strategies": [1], "(ES)": [2], "is": [3, 156], "a": [4, 69, 95, 120], "class": [5], "of": [6, 38, 86, 89, 99, 144], "powerful": [7], "black-box": [8], "optimisation": [9], "methods": [10], "that": [11, 137, 149], "are": [12], "highly": [13], "parallelisable": [14], "and": [15, 19, 123, 128, 166], "can": [16], "handle": [17], "non-differentiable": [18], "noisy": [20], "objectives.": [21], "However,": [22], "na\u00efve": [23], "ES": [24, 101, 110, 129, 174], "becomes": [25], "prohibitively": [26], "expensive": [27], "at": [28, 78], "scale": [29], "on": [30, 163], "GPUs": [31], "due": [32], "to": [33, 84, 112, 173], "the": [34, 87, 141], "low": [35], "arithmetic": [36, 58], "intensity": [37, 59], "batched": [39], "matrix": [40], "multiplications": [41], "with": [42, 158], "unstructured": [43], "random": [44], "perturbations.": [45], "We": [46, 93], "introduce": [47], "Guided": [49], "GeneRal": [50], "Optimisation": [51], "via": [52], "Low-rank": [53], "Learning": [54], "(EGGROLL),": [55], "which": [56], "improves": [57], "by": [60], "structuring": [61], "individual": [62], "perturbations": [63], "as": [64, 130], "rank-$r$": [65], "matrices,": [66], "resulting": [67], "in": [68, 72, 114, 152, 175], "hundredfold": [70], "increase": [71], "training": [73], "speed": [74], "for": [75, 102, 109, 160], "billion-parameter": [76], "models": [77, 148], "large": [79], "population": [80], "sizes,": [81], "achieving": [82], "up": [83], "91%": [85], "throughput": [88], "pure": [90], "batch": [91], "inference.": [92], "provide": [94], "rigorous": [96], "theoretical": [97], "analysis": [98], "Gaussian": [100], "high-dimensional": [103], "parameter": [104, 131], "objectives,": [105], "investigating": [106], "conditions": [107], "needed": [108], "updates": [111], "converge": [113], "high": [115], "dimensions.": [116], "Our": [117, 134], "results": [118], "reveal": [119], "linearising": [121], "effect,": [122], "proving": [124], "consistency": [125], "between": [126], "EGGROLL": [127], "dimension": [132], "increases.": [133], "experiments": [135], "show": [136], "EGGROLL:": [138], "(1)": [139], "enables": [140], "stable": [142], "pretraining": [143], "nonlinear": [145], "recurrent": [146], "language": [147], "operate": [150], "purely": [151], "integer": [153], "datatypes,": [154], "(2)": [155], "competitive": [157], "GRPO": [159], "post-training": [161], "LLMs": [162], "reasoning": [164], "tasks,": [165], "(3)": [167], "does": [168], "not": [169], "compromise": [170], "performance": [171], "compared": [172], "tabula": [176], "rasa": [177], "RL": [178], "settings,": [179], "despite": [180], "being": [181], "faster.": [182]}, "primary_topic": {"id": "https://openalex.org/T10100", "display_name": "Metaheuristic Optimization Algorithms Research", "score": 0.4733999967575073, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10100", "display_name": "Metaheuristic Optimization Algorithms Research", "score": 0.4733999967575073, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11612", "display_name": "Stochastic Gradient Optimization Techniques", "score": 0.4066999852657318, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11975", "display_name": "Evolutionary Algorithms and Applications", "score": 0.03660000115633011, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.16652", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.16652", "pdf_url": "https://arxiv.org/pdf/2511.16652", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7130682069", "doi": "https://doi.org/10.5281/zenodo.18712736", "title": "ENHANCING CODE-STYLE RECOGNITION WITH LLMS: DATASET SIZE CONSIDERATIONS", "publication_year": 2025, "publication_date": "2025-11-20", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5126463051", "display_name": "Mykhailovych Petrenko Oleksandr", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I98435010", "display_name": "Lviv Polytechnic National University", "ror": "https://ror.org/0542q3127", "country_code": "UA", "type": "education", "lineage": ["https://openalex.org/I98435010"]}], "countries": ["UA"], "is_corresponding": true, "raw_author_name": "Oleksandr, Mykhailovych Petrenko", "raw_affiliation_strings": ["Department of Applied Mathematics, Lviv Polytechnic National University, Ukraine"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Applied Mathematics, Lviv Polytechnic National University, Ukraine", "institution_ids": ["https://openalex.org/I98435010"]}]}], "abstract_inverted_index": {"One": [0], "aspect": [1], "of": [2, 44, 56, 69, 118, 144, 176, 199], "a": [3, 10], "well-written": [4], "codebase": [5], "is": [6, 50, 65, 90], "its": [7, 101], "adherence": [8, 184], "to": [9, 28, 60, 75, 105, 124, 146, 172, 185, 194], "particular": [11], "code": [12, 27, 78, 180], "style,": [13], "and": [14, 24, 100, 111, 139, 155, 161, 178, 183], "Large": [15], "Language": [16], "Models": [17], "(LLMs)": [18], "can": [19, 202], "greatly": [20], "assist": [21], "in": [22, 92, 188, 209], "reviewing": [23], "adapting": [25], "the": [26, 30, 42, 45, 53, 85, 107, 132, 174, 196], "follow": [29], "defined": [31], "conventions.": [32], "Because": [33], "specific": [34, 86], "code-style": [35], "rules": [36], "are": [37, 218], "typically": [38], "not": [39], "known": [40], "during": [41], "pre-training": [43], "base": [46], "model,": [47], "additional": [48], "fine-tuning": [49, 73, 207], "necessary.": [51], "However,": [52], "exact": [54], "number": [55, 198], "training": [57, 126, 200], "samples": [58, 201], "required": [59], "achieve": [61], "optimal": [62], "model": [63], "performance": [64], "unclear.": [66], "The": [67, 191], "significance": [68], "dataset": [70], "size": [71], "when": [72], "LLMs": [74, 177, 208], "categorize": [76], "Python": [77], "snippets": [79], "as": [80, 221], "compliant": [81], "or": [82, 215, 228], "noncompliant": [83], "with": [84, 135, 151], "PEP-8": [87], "indentation": [88], "rule": [89], "investigated": [91], "this": [93], "work.": [94], "We": [95], "used": [96, 193], "Low-Rank": [97], "Adaptation": [98], "(LoRA)": [99], "quantized": [102], "variant": [103], "(QLoRA)": [104], "fine-tune": [106], "Llama": [108, 112], "2": [109], "7B": [110], "3": [113], "8B": [114], "models": [115, 133], "on": [116, 169], "datasets": [117, 137, 153], "varying": [119], "sizes,": [120], "ranging": [121], "from": [122], "60": [123], "480": [125, 140], "samples.": [127], "Our": [128], "experiments": [129], "demonstrated": [130], "that": [131], "fine-tuned": [134], "larger": [136], "(240": [138], "samples)": [141, 157], "achieved": [142], "accuracies": [143], "up": [145], "99%,": [147], "whereas": [148], "those": [149], "trained": [150], "smaller": [152], "(60": [154], "120": [156], "experienced": [158], "over": [159], "fitting": [160], "lower": [162], "accuracy.": [163], "Subsequent": [164], "research": [165], "will": [166], "be": [167, 204], "based": [168], "these": [170], "findings": [171], "explore": [173], "potential": [175], "improve": [179], "readability,": [181], "maintainability,": [182], "coding": [186], "standards": [187], "software": [189], "development.": [190], "methodology": [192], "determine": [195], "sufficient": [197], "also": [203], "valuable": [205], "for": [206], "other": [210], "domains": [211], "where": [212], "strict": [213], "style": [214], "formatting": [216], "conventions": [217], "required,": [219], "such": [220], "legal": [222], "document": [223], "preparation,": [224], "standardized": [225], "medical": [226], "reporting,": [227], "financial": [229], "regulatory": [230], "filings.": [231]}, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.9970999956130981, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.9970999956130981, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0015999999595806003, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10430", "display_name": "Software Engineering Techniques and Practices", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.5281/zenodo.18712736", "is_oa": true, "landing_page_url": "https://doi.org/10.5281/zenodo.18712736", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400562", "display_name": "Zenodo (CERN European Organization for Nuclear Research)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I67311998", "host_organization_name": "European Organization for Nuclear Research", "host_organization_lineage": ["https://openalex.org/I67311998"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "article-journal"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406823419", "doi": "https://doi.org/10.2196/63755", "title": "Characterizing Public Sentiments and Drug Interactions in the COVID-19 Pandemic Using Social Media: Natural Language Processing and Network Analysis", "publication_year": 2025, "publication_date": "2025-01-25", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5020534921", "display_name": "Wanxin Li", "orcid": "https://orcid.org/0000-0002-7981-3228", "observed_orcids": ["https://orcid.org/0000-0002-7981-3228"]}, "institutions": [{"id": "https://openalex.org/I4210158318", "display_name": "Second Affiliated Hospital of Zhejiang University", "ror": "https://ror.org/059cjpv64", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210158318"]}, {"id": "https://openalex.org/I76130692", "display_name": "Zhejiang University", "ror": "https://ror.org/00a2xv884", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I76130692"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wanxin Li", "raw_affiliation_strings": ["School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China"], "raw_orcid": "https://orcid.org/0000-0002-7981-3228", "affiliations": [{"raw_affiliation_string": "School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China", "institution_ids": ["https://openalex.org/I4210158318", "https://openalex.org/I76130692"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5081953757", "display_name": "Yining Hua", "orcid": "https://orcid.org/0000-0001-7779-1208", "observed_orcids": ["https://orcid.org/0000-0001-7779-1208"]}, "institutions": [{"id": "https://openalex.org/I1283280774", "display_name": "Brigham and Women's Hospital", "ror": "https://ror.org/04b6nzv94", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283280774", "https://openalex.org/I48633490"]}, {"id": "https://openalex.org/I136199984", "display_name": "Harvard University", "ror": "https://ror.org/03vek6s52", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I136199984"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Yining Hua", "raw_affiliation_strings": ["Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, United States", "Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, MA, United States"], "raw_orcid": "https://orcid.org/0000-0001-7779-1208", "affiliations": [{"raw_affiliation_string": "Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, United States", "institution_ids": ["https://openalex.org/I136199984"]}, {"raw_affiliation_string": "Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, MA, United States", "institution_ids": ["https://openalex.org/I1283280774"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5116559848", "display_name": "Peilin Zhou", "orcid": "https://orcid.org/0000-0001-6763-5236", "observed_orcids": ["https://orcid.org/0000-0001-6763-5236"]}, "institutions": [{"id": "https://openalex.org/I4405261251", "display_name": "The Hong Kong University of Science and Technology (Guangzhou)", "ror": "https://ror.org/050h0vm43", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I4405261251"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Peilin Zhou", "raw_affiliation_strings": ["Thrust of Data Science and Analytics, Hong Kong University of Science and Technology, Guangzhou, China"], "raw_orcid": "https://orcid.org/0000-0001-6763-5236", "affiliations": [{"raw_affiliation_string": "Thrust of Data Science and Analytics, Hong Kong University of Science and Technology, Guangzhou, China", "institution_ids": ["https://openalex.org/I4405261251"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016290671", "display_name": "Li Zhou", "orcid": "https://orcid.org/0000-0003-3874-4833", "observed_orcids": ["https://orcid.org/0000-0003-3874-4833"]}, "institutions": [{"id": "https://openalex.org/I1283280774", "display_name": "Brigham and Women's Hospital", "ror": "https://ror.org/04b6nzv94", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283280774", "https://openalex.org/I48633490"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Li Zhou", "raw_affiliation_strings": ["Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, MA, United States"], "raw_orcid": "https://orcid.org/0000-0003-3874-4833", "affiliations": [{"raw_affiliation_string": "Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, MA, United States", "institution_ids": ["https://openalex.org/I1283280774"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062885337", "display_name": "Xin Xu", "orcid": "https://orcid.org/0000-0002-4639-6480", "observed_orcids": ["https://orcid.org/0000-0002-4639-6480"]}, "institutions": [{"id": "https://openalex.org/I4210158318", "display_name": "Second Affiliated Hospital of Zhejiang University", "ror": "https://ror.org/059cjpv64", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210158318"]}, {"id": "https://openalex.org/I76130692", "display_name": "Zhejiang University", "ror": "https://ror.org/00a2xv884", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I76130692"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xin Xu", "raw_affiliation_strings": ["School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China"], "raw_orcid": "https://orcid.org/0000-0002-4639-6480", "affiliations": [{"raw_affiliation_string": "School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China", "institution_ids": ["https://openalex.org/I4210158318", "https://openalex.org/I76130692"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5078108605", "display_name": "Jie Yang", "orcid": "https://orcid.org/0000-0001-5696-363X", "observed_orcids": ["https://orcid.org/0000-0001-5696-363X"]}, "institutions": [{"id": "https://openalex.org/I1283280774", "display_name": "Brigham and Women's Hospital", "ror": "https://ror.org/04b6nzv94", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283280774", "https://openalex.org/I48633490"]}, {"id": "https://openalex.org/I136199984", "display_name": "Harvard University", "ror": "https://ror.org/03vek6s52", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I136199984"]}, {"id": "https://openalex.org/I4210158318", "display_name": "Second Affiliated Hospital of Zhejiang University", "ror": "https://ror.org/059cjpv64", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210158318"]}, {"id": "https://openalex.org/I76130692", "display_name": "Zhejiang University", "ror": "https://ror.org/00a2xv884", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I76130692"]}], "countries": ["CN", "US"], "is_corresponding": false, "raw_author_name": "Jie Yang", "raw_affiliation_strings": ["Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States", "School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China"], "raw_orcid": "https://orcid.org/0000-0001-5696-363X", "affiliations": [{"raw_affiliation_string": "Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States", "institution_ids": ["https://openalex.org/I1283280774", "https://openalex.org/I136199984"]}, {"raw_affiliation_string": "School of Public Health, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China", "institution_ids": ["https://openalex.org/I4210158318", "https://openalex.org/I76130692"]}]}], "abstract_inverted_index": {"BACKGROUND:": [0], "While": [1], "the": [2, 50, 71, 99, 142, 152, 178, 218, 235, 250, 256, 261, 310], "COVID-19": [3, 179], "pandemic": [4, 51, 180], "has": [5], "induced": [6], "massive": [7], "discussion": [8], "of": [9, 73, 106, 260, 286, 295, 303, 325], "available": [10], "medications": [11], "on": [12, 19, 40, 77, 239, 248], "social": [13, 41, 74, 389], "media,": [14], "traditional": [15, 370], "studies": [16, 372], "focused": [17, 237], "only": [18, 251], "limited": [20], "aspects,": [21], "such": [22], "as": [23, 98, 309, 384], "public": [24, 236, 268, 334, 340, 360, 391], "opinions,": [25], "and": [26, 31, 55, 113, 122, 154, 165, 181, 188, 217, 227, 244, 246, 279, 305, 317, 327, 363, 375], "endured": [27], "reporting": [28], "biases,": [29], "inefficiency,": [30], "long": [32], "collection": [33], "times.": [34], "OBJECTIVE:": [35], "Harnessing": [36], "drug-related": [37, 297], "data": [38, 368], "posted": [39], "media": [42, 75, 276], "in": [43, 342], "real-time": [44], "can": [45, 353, 364], "offer": [46, 365], "insights": [47], "into": [48], "how": [49], "impacts": [52], "drug": [53, 89, 155, 162, 182, 254, 287], "use": [54], "monitor": [56], "misinformation.": [57], "This": [58, 81, 101, 346], "study": [59, 82, 347], "aimed": [60], "to": [61, 115, 125, 136, 146, 158, 173, 177, 382], "develop": [62], "a": [63, 84, 194, 355, 385], "natural": [64], "language": [65, 94], "processing": [66], "(NLP)": [67], "pipeline": [68, 86, 102, 170, 352], "tailored": [69], "for": [70, 87, 129, 333, 358, 369, 387], "analysis": [72, 135, 157, 232, 259, 290, 320], "discourse": [76], "COVID-19-related": [78, 88, 198], "drugs.": [79], "METHODS:": [80], "constructed": [83], "full": [85], "tweet": [90], "analysis,": [91, 132], "using": [92], "pretrained": [93], "model-based": [95], "NLP": [96], "techniques": [97], "backbone.": [100], "is": [103], "architecturally": [104], "composed": [105], "4": [107], "core": [108], "modules:": [109], "named": [110, 204], "entity": [111, 205], "recognition": [112, 206], "normalization": [114], "identify": [116], "medical": [117], "entities": [118], "from": [119, 200, 213], "relevant": [120, 210], "tweets": [121, 175, 199, 211], "standardize": [123], "them": [124], "uniform": [126], "medication": [127], "names": [128], "time": [130], "trend": [131, 231], "target": [133], "sentiment": [134, 138], "reveal": [137], "polarities": [139], "associated": [140], "with": [141, 299], "entities,": [143], "topic": [144], "modeling": [145], "understand": [147], "underlying": [148], "themes": [149], "discussed": [150, 313], "by": [151, 273], "population,": [153], "network": [156, 319], "dig": [159], "potential": [160], "adverse": [161], "reactions": [163], "(ADR)": [164], "drug-drug": [166], "interactions": [167], "(DDI).": [168], "The": [169, 377], "was": [171, 270], "deployed": [172], "analyze": [174], "related": [176], "therapies": [183], "between": [184], "February": [185], "1,": [186], "2020,": [187], "April": [189], "30,": [190], "2022.": [191], "RESULTS:": [192], "From": [193], "dataset": [195], "comprising": [196], "169,659,956": [197], "103,682,686": [201], "users,": [202, 216], "our": [203], "model": [207], "identified": [208, 322], "2,124,757": [209], "sourced": [212], "1,800,372": [214], "unique": [215], "top": [219, 262], "5": [220, 263], "most-discussed": [221, 264], "drugs:": [222], "ivermectin,": [223], "hydroxychloroquine,": [224], "remdesivir,": [225, 249], "zinc,": [226], "vitamin": [228], "D.": [229], "Time": [230], "revealed": [233, 266], "that": [234, 267, 329, 349], "mostly": [238], "repurposed": [240], "drugs": [241, 265], "(ie,": [242], "hydroxychloroquine": [243], "ivermectin),": [245], "least": [247], "officially": [252], "approved": [253], "among": [255], "5.": [257], "Sentiment": [258], "perception": [269], "predominantly": [271], "shaped": [272], "celebrity": [274], "endorsements,": [275], "hot": [277], "spots,": [278], "governmental": [280], "directives": [281], "rather": [282], "than": [283], "empirical": [284], "evidence": [285], "efficacy.": [288], "Topic": [289], "obtained": [291], "15": [292], "general": [293], "topics": [294], "overall": [296], "tweets,": [298], "\"clinical": [300], "treatment": [301], "effects": [302], "drugs\"": [304], "\"physical": [306], "symptoms\"": [307], "emerging": [308, 323], "most": [311], "frequently": [312], "topics.": [314], "Co-occurrence": [315], "matrices": [316], "complex": [318], "further": [321], "patterns": [324], "DDI": [326, 374], "ADR": [328], "could": [330], "be": [331, 354], "critical": [332], "health": [335, 361, 392], "surveillance": [336], "like": [337], "better": [338], "safeguarding": [339], "safety": [341], "medicines": [343], "use.": [344], "CONCLUSIONS:": [345], "shows": [348], "an": [350], "NLP-based": [351], "robust": [356], "tool": [357], "large-scale": [359], "monitoring": [362], "valuable": [366], "supplementary": [367], "epidemiological": [371], "concerning": [373], "ADR.": [376], "framework": [378], "presented": [379], "here": [380], "aspires": [381], "serve": [383], "cornerstone": [386], "future": [388], "media-based": [390], "analytics.": [393]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9063000082969666, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9063000082969666, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11943", "display_name": "Pharmacovigilance and Adverse Drug Reactions", "score": 0.054999999701976776, "subfield": {"id": "https://openalex.org/subfields/3005", "display_name": "Toxicology"}, "field": {"id": "https://openalex.org/fields/30", "display_name": "Pharmacology, Toxicology and Pharmaceutics"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.010599999688565731, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.2196/63755", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/63755", "pdf_url": "https://www.jmir.org/2025/1/e63755/PDF", "source": {"id": "https://openalex.org/S17147534", "display_name": "Journal of Medical Internet Research", "issn_l": "1438-8871", "issn": ["1438-8871", "1439-4456"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "doyens", "jufo-2", "ki-jl-2", "medline", "norway-2"], "host_organization": "https://openalex.org/P4310320608", "host_organization_name": "JMIR Publications", "host_organization_lineage": ["https://openalex.org/P4310320608"], "host_organization_lineage_names": ["JMIR Publications"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Medical Internet Research", "raw_type": "journal-article"}, "cited_by_count": 9, "is_retracted": false}, {"id": "https://openalex.org/W7171699471", "doi": "https://doi.org/10.5281/zenodo.21682010", "title": "GENERATIVE PRETRAINED TRANSFORMERS FOR INVESTOR-CENTRIC PORTFOLIO CONSTRUCTION", "publication_year": 2025, "publication_date": "2025-05-31", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5045065292", "display_name": "Dimitris Papakyriakopoulos", "orcid": "https://orcid.org/0009-0002-5262-0669", "observed_orcids": ["https://orcid.org/0009-0002-5262-0669"]}, "institutions": [{"id": "https://openalex.org/I73142707", "display_name": "Athens University of Economics and Business", "ror": "https://ror.org/03s262162", "country_code": "GR", "type": "education", "lineage": ["https://openalex.org/I73142707"]}], "countries": ["GR"], "is_corresponding": false, "raw_author_name": "Dimitrios PAPAKYRIAKOPOULOS", "raw_affiliation_strings": ["Athens University of Economics and Business, Greece"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Athens University of Economics and Business, Greece", "institution_ids": ["https://openalex.org/I73142707"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5062572892", "display_name": "Manolis N. Kritikos", "orcid": "https://orcid.org/0000-0002-4687-4171", "observed_orcids": ["https://orcid.org/0000-0002-4687-4171"]}, "institutions": [{"id": "https://openalex.org/I73142707", "display_name": "Athens University of Economics and Business", "ror": "https://ror.org/03s262162", "country_code": "GR", "type": "education", "lineage": ["https://openalex.org/I73142707"]}], "countries": ["GR"], "is_corresponding": false, "raw_author_name": "Manolis KRITIKOS", "raw_affiliation_strings": ["Athens University of Economics and Business, Greece"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Athens University of Economics and Business, Greece", "institution_ids": ["https://openalex.org/I73142707"]}]}], "abstract_inverted_index": {"The": [0, 50, 115], "objective": [1], "of": [2, 10, 102, 122, 137], "this": [3], "paper": [4], "is": [5], "to": [6, 23, 35, 56, 106, 118, 141], "examine": [7], "the": [8, 54, 81, 86, 100, 119, 135], "application": [9], "generative": [11, 27, 138], "artificial": [12], "intelligence": [13], "in": [14, 128], "personalized": [15], "portfolio": [16, 58], "construction": [17], "and": [18, 74, 94, 110, 130, 143], "evaluate": [19], "its": [20], "performance": [21, 62], "relative": [22], "traditional": [24], "benchmarks.": [25], "A": [26], "AI": [28], "model,": [29], "specifically": [30], "OpenAI's": [31], "GPT-4o,": [32], "was": [33], "employed": [34], "construct": [36], "investment": [37, 48, 87, 113], "portfolios": [38, 79], "for": [39, 134], "ten": [40], "virtual": [41], "investor": [42], "profiles": [43], "over": [44, 85], "a": [45, 132], "fixed": [46], "three-month": [47], "horizon.": [49], "methodology": [51], "involved": [52], "prompting": [53], "model": [55], "create": [57], "allocations,": [59], "followed": [60], "by": [61], "evaluation": [63], "using": [64], "financial": [65, 108], "metrics": [66], "including": [67], "total": [68], "return,": [69], "volatility,": [70], "beta,": [71], "Sharpe": [72], "ratio,": [73], "maximum": [75], "drawdown.": [76], "All": [77], "AI-generated": [78], "outperformed": [80], "S&P": [82], "500": [83], "index": [84], "period,": [88], "demonstrating": [89], "stronger": [90], "risk-": [91], "adjusted": [92], "returns": [93], "lower": [95], "drawdowns.": [96], "These": [97], "results": [98], "highlight": [99], "potential": [101], "large": [103], "language": [104], "models": [105, 139], "synthesize": [107], "data": [109], "produce": [111], "competitive": [112], "strategies.": [114], "study": [116], "contributes": [117], "growing": [120], "body": [121], "research": [123], "on": [124], "AI-driven": [125], "decision-": [126], "making": [127], "finance": [129], "provides": [131], "foundation": [133], "development": [136], "tailored": [140], "asset": [142], "wealth": [144], "management": [145]}, "primary_topic": {"id": "https://openalex.org/T11326", "display_name": "Stock Market Forecasting Methods", "score": 0.4740999937057495, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T11326", "display_name": "Stock Market Forecasting Methods", "score": 0.4740999937057495, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11413", "display_name": "Risk and Portfolio Optimization", "score": 0.39259999990463257, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10047", "display_name": "Financial Markets and Investment Strategies", "score": 0.044599998742341995, "subfield": {"id": "https://openalex.org/subfields/2003", "display_name": "Finance"}, "field": {"id": "https://openalex.org/fields/20", "display_name": "Economics, Econometrics and Finance"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.5281/zenodo.21682010", "is_oa": true, "landing_page_url": "https://doi.org/10.5281/zenodo.21682010", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400562", "display_name": "Zenodo (CERN European Organization for Nuclear Research)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I67311998", "host_organization_name": "European Organization for Nuclear Research", "host_organization_lineage": ["https://openalex.org/I67311998"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "JournalArticle"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4413916654", "doi": "https://doi.org/10.1007/s10278-025-01636-x", "title": "Comparative Evaluation of Deep Learning and Foundation Model Embeddings for Osteoarthritis Feature Classification in Knee Radiographs", "publication_year": 2025, "publication_date": "2025-09-02", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5009060599", "display_name": "Mohammadreza Chavoshi", "orcid": "https://orcid.org/0000-0001-6598-7190", "observed_orcids": ["https://orcid.org/0000-0001-6598-7190"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Mohammadreza Chavoshi", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050086721", "display_name": "Hari Trivedi", "orcid": "https://orcid.org/0000-0001-6648-8334", "observed_orcids": ["https://orcid.org/0000-0001-6648-8334"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Hari Trivedi", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5001041013", "display_name": "Janice M. Newsome", "orcid": "https://orcid.org/0000-0002-2472-3815", "observed_orcids": ["https://orcid.org/0000-0002-2472-3815"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Janice Newsome", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5004236540", "display_name": "Aawez Mansuri", "orcid": "https://orcid.org/0009-0006-7017-4358", "observed_orcids": ["https://orcid.org/0009-0006-7017-4358"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Aawez Mansuri", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042209918", "display_name": "Frank Li", "orcid": "https://orcid.org/0000-0002-8205-3397", "observed_orcids": ["https://orcid.org/0000-0002-8205-3397"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Frank Li", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5037108911", "display_name": "Theo Dapamede", "orcid": "https://orcid.org/0000-0002-6264-2282", "observed_orcids": ["https://orcid.org/0000-0002-6264-2282"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Theo Dapamede", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5041981029", "display_name": "Bardia Khosravi", "orcid": "https://orcid.org/0000-0002-8024-339X", "observed_orcids": ["https://orcid.org/0000-0002-8024-339X"]}, "institutions": [{"id": "https://openalex.org/I1330342723", "display_name": "Mayo Clinic", "ror": "https://ror.org/02qp3tb03", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1330342723"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Bardia Khosravi", "raw_affiliation_strings": ["Department of Radiology, Mayo Clinic, Rochester, MN, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiology, Mayo Clinic, Rochester, MN, USA", "institution_ids": ["https://openalex.org/I1330342723"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5076075666", "display_name": "Judy Wawira Gichoya", "orcid": "https://orcid.org/0000-0002-1097-316X", "observed_orcids": ["https://orcid.org/0000-0002-1097-316X"]}, "institutions": [{"id": "https://openalex.org/I150468666", "display_name": "Emory University", "ror": "https://ror.org/03czfpz43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I150468666"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Judy Gichoya", "raw_affiliation_strings": ["Department of Radiology, Emory University, Atlanta, GA, USA. judywawira@emory.edu", "Department of Radiology, Emory University, Atlanta, GA, USA"], "raw_orcid": "https://orcid.org/0000-0002-1097-316X", "affiliations": [{"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA. judywawira@emory.edu", "institution_ids": ["https://openalex.org/I150468666"]}, {"raw_affiliation_string": "Department of Radiology, Emory University, Atlanta, GA, USA", "institution_ids": ["https://openalex.org/I150468666"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.49950000643730164, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.49950000643730164, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T14510", "display_name": "Medical Imaging and Analysis", "score": 0.18459999561309814, "subfield": {"id": "https://openalex.org/subfields/2204", "display_name": "Biomedical Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12422", "display_name": "Radiomics and Machine Learning in Medical Imaging", "score": 0.10639999806880951, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.1007/s10278-025-01636-x", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s10278-025-01636-x", "pdf_url": null, "source": {"id": "https://openalex.org/S62275304", "display_name": "Journal of Imaging Informatics in Medicine", "issn_l": "0897-1889", "issn": ["0897-1889", "1618-727X", "2948-2925", "2948-2933"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-1", "ki-jl-1", "medline", "norway-1"], "host_organization": "https://openalex.org/P4310319900", "host_organization_name": "Springer Science+Business Media", "host_organization_lineage": ["https://openalex.org/P4310319900", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Science+Business Media", "Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Imaging Informatics in Medicine", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4416100421", "doi": "https://doi.org/10.2196/preprints.87477", "title": "Temperature-based calibration of pretrained language models for automated systematic review screening of biomedical literature (Preprint)", "publication_year": 2025, "publication_date": "2025-11-10", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5067648153", "display_name": "Gary Chan", "orcid": "https://orcid.org/0000-0002-7569-1948", "observed_orcids": ["https://orcid.org/0000-0002-7569-1948"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gary C.K. Chan", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-7569-1948", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000618392", "display_name": "Jiayuan He", "orcid": "https://orcid.org/0000-0002-8994-9532", "observed_orcids": ["https://orcid.org/0000-0002-8994-9532"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Estrid He", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-8994-9532", "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5067214173", "display_name": "Karin M. Verspoor", "orcid": "https://orcid.org/0000-0002-8661-1544", "observed_orcids": ["https://orcid.org/0000-0002-8661-1544"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Karin Verspoor", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-8661-1544", "affiliations": []}], "abstract_inverted_index": {"BACKGROUND": [0], "Systematic": [1], "reviews": [2, 88], "are": [3], "essential": [4], "to": [5, 36, 156, 172], "evidence-based": [6], "health": [7], "research,": [8], "but": [9], "manually": [10], "screening": [11, 100], "titles": [12], "and": [13, 17, 48, 54, 94, 111, 127, 143, 217], "abstracts": [14], "is": [15], "time-consuming": [16], "labour-intensive.": [18], "Pretrained": [19], "language": [20], "models": [21, 28, 96], "(PLMs)": [22], "offer": [23], "automation": [24], "potential,": [25], "yet": [26], "these": [27], "may": [29], "be": [30], "overconfident": [31], "in": [32, 67, 227], "their": [33, 46], "decision": [34], "due": [35], "suboptimal": [37], "calibration,": [38], "especially": [39], "when": [40], "facing": [41], "distribution": [42, 146, 184], "shifts.": [43], "This": [44], "limits": [45], "trustworthiness": [47], "practical": [49], "application.": [50], "OBJECTIVE": [51], "To": [52], "evaluate": [53], "compare": [55], "three": [56, 116, 150], "temperature": [57, 120, 124, 134, 160], "scaling": [58, 125, 161], "methods": [59, 152], "for": [60, 99, 166, 190, 199], "improving": [61], "the": [62, 78, 144, 163], "calibration": [63, 108, 151, 165, 188, 195], "of": [64, 85], "PLMs": [65, 212], "used": [66], "systematic": [68, 87, 201], "review": [69, 202], "screening,": [70], "including": [71], "a": [72, 83, 140], "novel": [73, 130], "review-specific": [74, 131], "approach": [75], "based": [76, 135], "on": [77, 136, 224], "Mahalanobis": [79, 137, 178], "distance.": [80], "METHODS": [81], "Using": [82], "dataset": [84], "8,608": [86], "comprising": [89], "over": [90], "540,000": [91], "abstracts,": [92], "BERT": [93], "BioBERT": [95], "were": [97], "fine-tuned": [98], "tasks.": [101], "Calibration": [102], "performance": [103, 154], "was": [104], "assessed": [105], "using": [106], "expected": [107], "error": [109], "(ECE)": [110], "negative": [112], "log-likelihood": [113], "(NLL)": [114], "across": [115], "methods:": [117], "1.": [118], "Standard": [119, 159], "scaling,": [121], "2.": [122], "Parameterized": [123], "(PTS),": [126], "3.": [128], "A": [129], "method": [132, 180], "adapting": [133], "distance": [138], "between": [139], "review\u2019s": [141], "embedding": [142], "training": [145], "centroid.": [147], "RESULTS": [148], "All": [149], "improved": [153], "compared": [155], "uncalibrated": [157], "models.": [158], "achieved": [162], "best": [164], "in-distribution": [167], "topics,": [168], "while": [169], "PTS": [170], "tended": [171], "overfit": [173], "validation": [174], "data.": [175], "The": [176], "proposed": [177], "distance\u2013based": [179], "outperformed": [181], "others": [182], "under": [183], "shift,": [185], "showing": [186], "lower": [187], "errors": [189], "out-of-distribution": [191], "reviews.": [192, 229], "CONCLUSIONS": [193], "Review-specific": [194], "enhances": [196], "model": [197, 206], "reliability": [198], "automated": [200], "screening.": [203], "By": [204], "aligning": [205], "confidence": [207], "with": [208], "empirical": [209], "probabilities,": [210], "calibrated": [211], "support": [213], "better": [214], "uncertainty": [215], "handling": [216], "more": [218], "principled": [219], "stopping": [220], "rules,": [221], "reducing": [222], "dependence": [223], "arbitrary": [225], "heuristics": [226], "technology-assisted": [228]}, "primary_topic": {"id": "https://openalex.org/T10206", "display_name": "Meta-analysis and systematic reviews", "score": 0.7534000277519226, "subfield": {"id": "https://openalex.org/subfields/1804", "display_name": "Statistics, Probability and Uncertainty"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T10206", "display_name": "Meta-analysis and systematic reviews", "score": 0.7534000277519226, "subfield": {"id": "https://openalex.org/subfields/1804", "display_name": "Statistics, Probability and Uncertainty"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.1315000057220459, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.025800000876188278, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.2196/preprints.87477", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/preprints.87477", "pdf_url": null, "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416245705", "doi": "https://doi.org/10.48550/arxiv.2510.18918", "title": "Misinformation Detection using Large Language Models with Explainability", "publication_year": 2025, "publication_date": "2025-10-21", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Patel, Jainee", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Patel, Jainee", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025539382", "display_name": "Chintan Bhatt", "orcid": "https://orcid.org/0000-0002-0423-0159", "observed_orcids": ["https://orcid.org/0000-0002-0423-0159"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bhatt, Chintan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076801437", "display_name": "Himani Trivedi", "orcid": "https://orcid.org/0009-0005-9054-2974", "observed_orcids": ["https://orcid.org/0009-0005-9054-2974", "https://orcid.org/0000-0002-5039-6424"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Trivedi, Himani", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5085593383", "display_name": "Thanh Thi Nguyen", "orcid": "https://orcid.org/0000-0001-9709-1663", "observed_orcids": ["https://orcid.org/0000-0001-9709-1663"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nguyen, Thanh Thi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"The": [0, 179], "rapid": [1], "spread": [2], "of": [3, 89], "misinformation": [4, 28, 198], "on": [5], "online": [6], "platforms": [7], "undermines": [8], "trust": [9], "among": [10], "individuals": [11], "and": [12, 22, 39, 50, 77, 91, 113, 162, 173, 188], "hinders": [13], "informed": [14], "decision": [15], "making.": [16], "This": [17, 139], "paper": [18], "shows": [19, 148], "an": [20, 166, 192], "explainable": [21, 167], "computationally": [23], "efficient": [24], "pipeline": [25, 168], "to": [26, 109, 131], "detect": [27], "using": [29, 41], "transformer-based": [30], "pretrained": [31], "language": [32], "models": [33], "(PLMs).": [34], "We": [35], "optimize": [36], "both": [37], "RoBERTa": [38, 132], "DistilBERT": [40, 127], "a": [42, 86, 150], "two-step": [43], "strategy:": [44], "first,": [45], "we": [46, 57, 80, 97], "freeze": [47], "the": [48, 53, 60, 82, 99, 106, 119], "backbone": [49, 61], "train": [51], "only": [52], "classification": [54], "head;": [55], "then,": [56], "progressively": [58], "unfreeze": [59], "layers": [62], "while": [63, 133, 157], "applying": [64], "layer-wise": [65], "learning": [66], "rate": [67], "decay.": [68], "On": [69], "two": [70, 142], "real-world": [71], "benchmark": [72], "datasets,": [73], "COVID": [74], "Fake": [75], "News": [76], "FakeNewsNet": [78], "GossipCop,": [79], "test": [81], "proposed": [83], "approach": [84], "with": [85, 185], "unified": [87], "protocol": [88], "preprocessing": [90], "stratified": [92], "splits.": [93], "To": [94], "ensure": [95], "transparency,": [96], "integrate": [98], "Local": [100], "Interpretable": [101], "Model-Agnostic": [102], "Explanations": [103], "(LIME)": [104], "at": [105, 118], "token": [107], "level": [108], "present": [110], "token-level": [111], "rationales": [112], "SHapley": [114], "Additive": [115], "exPlanations": [116], "(SHAP)": [117], "global": [120, 174], "feature": [121], "attribution": [122], "level.": [123], "It": [124], "demonstrates": [125], "that": [126, 149, 169, 182], "achieves": [128], "accuracy": [129], "comparable": [130], "requiring": [134], "significantly": [135], "less": [136], "computational": [137, 160], "resources.": [138], "work": [140], "makes": [141], "key": [143], "contributions:": [144], "(1)": [145], "it": [146, 164], "quantitatively": [147], "lightweight": [151], "PLM": [152], "can": [153, 190], "maintain": [154], "task": [155], "performance": [156], "substantially": [158], "reducing": [159], "cost,": [161], "(2)": [163], "presents": [165], "retrieves": [170], "faithful": [171], "local": [172], "justifications": [175], "without": [176], "compromising": [177], "performance.": [178], "results": [180], "suggest": [181], "PLMs": [183], "combined": [184], "principled": [186], "fine-tuning": [187], "interpretability": [189], "be": [191], "effective": [193], "framework": [194], "for": [195], "scalable,": [196], "trustworthy": [197], "detection.": [199]}, "primary_topic": {"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2510.18918", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.18918", "pdf_url": "https://arxiv.org/pdf/2510.18918", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415700444", "doi": "https://doi.org/10.62241/ijimds.11.2434.2547", "title": "Fine-Tuning Transformer Models for Enhanced Financial Sentiment Detection", "publication_year": 2025, "publication_date": "2025-07-28", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5120189986", "display_name": "Laarbaoui Ahmed", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210119856", "display_name": "Universit\u00e9 Sultan Moulay Slimane", "ror": "https://ror.org/02m8tb249", "country_code": "MA", "type": "education", "lineage": ["https://openalex.org/I4210119856"]}], "countries": ["MA"], "is_corresponding": true, "raw_author_name": "Laarbaoui Ahmed", "raw_affiliation_strings": ["Faculty of Sciences and Techniques , Sultan Moulay Slimane University , Beni Mellal , Morocco"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Faculty of Sciences and Techniques , Sultan Moulay Slimane University , Beni Mellal , Morocco", "institution_ids": ["https://openalex.org/I4210119856"]}]}], "abstract_inverted_index": {"Financial": [0, 26], "text": [1, 20, 68], "mining": [2, 21, 69], "is": [3, 29], "gaining": [4], "popularity.": [5], "Advancements": [6], "in": [7, 18, 41, 60, 103, 133], "deep": [8], "learning-based": [9], "models": [10, 117, 132, 150, 159], "on": [11, 93, 151], "generic": [12], "corpus": [13], "have": [14], "shown": [15], "promising": [16], "results": [17, 174], "financial": [19, 43, 67, 104, 127, 152, 189, 205], "applications,": [22], "including": [23], "sentiment": [24, 27, 158, 206], "analysis.": [25], "research": [28], "challenging": [30], "due": [31, 54], "to": [32, 55, 65, 76], "the": [33, 42, 56], "lack": [34], "of": [35, 148], "labeled": [36, 82], "data": [37], "and": [38, 124, 142, 153, 194], "specialized": [39], "terminology": [40], "area.": [44], "Deep": [45], "learning": [46, 75, 201], "algorithms": [47], "for": [48, 86, 182], "general": [49, 154], "usage": [50], "are": [51, 84, 191], "less": [52], "successful": [53], "particular": [57], "language": [58, 79, 88], "used": [59], "finance.": [61], "This": [62], "work": [63], "aims": [64], "improve": [66, 97, 101], "performance": [70, 102, 177], "by": [71], "utilizing": [72], "NLP": [73, 105, 199], "transfer": [74, 200], "enhance": [77], "pre-trained": [78], "models.": [80], "Limited": [81], "samples": [83], "needed": [85], "pretrained": [87, 116], "models,": [89], "but": [90], "training": [91, 147, 171], "them": [92], "domain-specific": [94], "corpora": [95], "can": [96], "their": [98], "performance.": [99], "To": [100], "tasks,": [106], "we": [107], "offer": [108], "an": [109], "upgraded": [110], "model": [111], "called": [112], "\\finsentiment,": [113], "which": [114], "combines": [115], "like": [118], "BERT,": [119], "XLNet,": [120, 138], "RoBERTa,": [121], "GPT,": [122], "Llama,": [123], "T5": [125], "with": [126, 165], "domain": [128], "corpora.": [129, 155], "The": [130], "finance-specific": [131, 157], "\\finsentiment": [134], "include": [135], "Fin-BERT,": [136], "Fin-": [137], "Fin-RoBERTa,": [139], "Fin-GPT,": [140], "Fin-Llama,": [141], "Fin-T5.": [143], "We": [144, 196], "suggest": [145], "combined": [146], "these": [149, 183], "Our": [156, 173], "outperform": [160], "across": [161, 178], "three": [162], "datasets,": [163], "even": [164], "limited": [166], "fine-tuning": [167], "using": [168], "a": [169], "smaller": [170], "set.": [172], "show": [175], "improved": [176], "all": [179], "examined": [180], "parameters": [181], "datasets.": [184], "Research": [185], "shows": [186], "that": [187, 198], "RoBERTa-pretrained": [188], "corporations": [190], "highly": [192], "effective": [193], "resilient.": [195], "demonstrate": [197], "approaches": [202], "effectively": [203], "address": [204], "analysis": [207], "challenges.": [208]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9970999956130981, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9970999956130981, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11326", "display_name": "Stock Market Forecasting Methods", "score": 0.0019000000320374966, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0006000000284984708, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.62241/ijimds.11.2434.2547", "is_oa": true, "landing_page_url": "https://doi.org/10.62241/ijimds.11.2434.2547", "pdf_url": "https://ijimds.org/articles/a-deep-learning-based-framework-for-dynamic-ecommerce-recommendation-using-online-reviews-and-product-features-2025-09-09/download", "source": {"id": "https://openalex.org/S5407053228", "display_name": "International Journal of Intelligent Management and Data Systems", "issn_l": "3119-6047", "issn": ["3119-6047"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Intelligent Management and Data Systems", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4414315804", "doi": "https://doi.org/10.1101/2025.09.14.676130", "title": "Protein Language Models Capture Structural and Functional Epistasis in a Zero-Shot Setting", "publication_year": 2025, "publication_date": "2025-09-17", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5080914112", "display_name": "Ananthan Nambiar", "orcid": "https://orcid.org/0000-0002-9767-9456", "observed_orcids": ["https://orcid.org/0000-0002-9767-9456"]}, "institutions": [{"id": "https://openalex.org/I201448701", "display_name": "University of Washington", "ror": "https://ror.org/00cvxb145", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I201448701"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Ananthan Nambiar", "raw_affiliation_strings": ["University of Washington;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Washington;", "institution_ids": ["https://openalex.org/I201448701"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115747137", "display_name": "Sayantani B. Littlefield", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Sayantani B. Littlefield", "raw_affiliation_strings": ["University of Illinois at Urbana-Champaign;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Illinois at Urbana-Champaign;", "institution_ids": ["https://openalex.org/I157725225"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5075487680", "display_name": "Carlos Cuellar", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Carlos Cuellar", "raw_affiliation_strings": ["University of Illinois Urbana-Champaign"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Illinois Urbana-Champaign", "institution_ids": ["https://openalex.org/I157725225"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119663624", "display_name": "Rohit Khorana", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Rohit Khorana", "raw_affiliation_strings": ["University of Illinois Urbana-Champaign"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Illinois Urbana-Champaign", "institution_ids": ["https://openalex.org/I157725225"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5017591427", "display_name": "Sergei Maslov", "orcid": "https://orcid.org/0000-0002-3701-492X", "observed_orcids": ["https://orcid.org/0000-0002-3701-492X"]}, "institutions": [{"id": "https://openalex.org/I157725225", "display_name": "University of Illinois Urbana-Champaign", "ror": "https://ror.org/047426m28", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I157725225"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Sergei Maslov", "raw_affiliation_strings": ["University of Illinois Urbana-Champaign"], "raw_orcid": "https://orcid.org/0000-0002-3701-492X", "affiliations": [{"raw_affiliation_string": "University of Illinois Urbana-Champaign", "institution_ids": ["https://openalex.org/I157725225"]}]}], "abstract_inverted_index": {"Abstract": [0], "Protein": [1], "language": [2], "models": [3], "(PLMs)": [4], "learn": [5], "from": [6, 66, 120], "large": [7], "collections": [8], "of": [9, 34], "natural": [10], "sequences": [11], "and": [12, 117, 124], "achieve": [13], "striking": [14], "success": [15], "across": [16], "prediction": [17], "tasks,": [18], "yet": [19], "it": [20], "remains": [21], "unclear": [22], "what": [23, 47], "biological": [24, 133], "principles": [25, 134], "underlie": [26], "their": [27, 137], "representations.": [28, 138], "We": [29], "use": [30], "epistasis,": [31], "the": [32, 96, 101, 132], "dependence": [33], "a": [35, 43, 88, 128], "mutation\u2019s": [36], "effect": [37], "on": [38, 71], "its": [39], "sequence": [40, 121], "context,": [41], "as": [42], "lens": [44], "to": [45, 91], "probe": [46], "PLMs": [48, 83, 113], "capture": [49, 114], "about": [50], "proteins.": [51], "Comparing": [52], "PLM-derived": [53], "scores": [54, 76], "with": [55, 78], "deep": [56], "mutational": [57], "scanning": [58], "data,": [59], "we": [60], "find": [61], "that": [62, 82, 112, 125], "epistasis": [63, 126], "emerges": [64], "naturally": [65], "pretrained": [67], "models,": [68], "without": [69], "supervision": [70], "experimental": [72, 97], "fitness.": [73], "Raw": [74], "model": [75, 93], "align": [77], "residue\u2013residue": [79], "contacts,": [80], "indicating": [81], "internalize": [84], "structural": [85, 116], "proximity.": [86], "Applying": [87], "nonlinear": [89], "transformation": [90], "bring": [92], "outputs": [94], "onto": [95], "scale,": [98], "however,": [99], "shifts": [100], "signal": [102], "toward": [103], "functional": [104, 118], "couplings": [105], "between": [106], "distant": [107], "sites.": [108], "These": [109], "findings": [110], "show": [111], "both": [115], "dependencies": [119], "data": [122], "alone,": [123], "provides": [127], "powerful": [129], "window": [130], "into": [131], "embedded": [135], "in": [136]}, "primary_topic": {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.47049999237060547, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.47049999237060547, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10044", "display_name": "Protein Structure and Dynamics", "score": 0.4381999969482422, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T11764", "display_name": "Evolution and Genetic Dynamics", "score": 0.02319999970495701, "subfield": {"id": "https://openalex.org/subfields/1311", "display_name": "Genetics"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "doi:10.1101/2025.09.14.676130", "is_oa": true, "landing_page_url": "https://doi.org/10.1101/2025.09.14.676130", "pdf_url": null, "source": {"id": "https://openalex.org/S4306402567", "display_name": "bioRxiv (Cold Spring Harbor Laboratory)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I2750212522", "host_organization_name": "Cold Spring Harbor Laboratory", "host_organization_lineage": ["https://openalex.org/I2750212522"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": "bioRxiv", "raw_type": "posted-content"}, "cited_by_count": 4, "is_retracted": false}, {"id": "https://openalex.org/W4411334349", "doi": "https://doi.org/10.1016/j.knosys.2025.113880", "title": "IMFND: In-context multimodal fake news detection with large visual-language models", "publication_year": 2025, "publication_date": "2025-06-16", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5013477562", "display_name": "Ye Jiang", "orcid": "https://orcid.org/0000-0002-6683-0205", "observed_orcids": ["https://orcid.org/0000-0002-6683-0205"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ye Jiang", "raw_affiliation_strings": ["College of Information Science and Technology, Qingdao University of Science and Technology, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information Science and Technology, Qingdao University of Science and Technology, China", "institution_ids": ["https://openalex.org/I143413998"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5023117058", "display_name": "Yimin Wang", "orcid": "https://orcid.org/0000-0002-8835-3825", "observed_orcids": ["https://orcid.org/0000-0002-8835-3825"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Yimin Wang", "raw_affiliation_strings": ["College of Data Science, Qingdao University of Science and Technology, China"], "raw_orcid": "https://orcid.org/0000-0002-8835-3825", "affiliations": [{"raw_affiliation_string": "College of Data Science, Qingdao University of Science and Technology, China", "institution_ids": ["https://openalex.org/I143413998"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9878000020980835, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T11147", "display_name": "Misinformation and Its Impacts", "score": 0.9878000020980835, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.009700000286102295, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0003000000142492354, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.knosys.2025.113880", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.knosys.2025.113880", "pdf_url": null, "source": {"id": "https://openalex.org/S10169007", "display_name": "Knowledge-Based Systems", "issn_l": "0950-7051", "issn": ["0950-7051", "1872-7409"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-2", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Knowledge-Based Systems", "raw_type": "journal-article"}, "cited_by_count": 12, "is_retracted": false}, {"id": "https://openalex.org/W4415785232", "doi": "https://doi.org/10.14569/ijacsa.2025.0161019", "title": "Evaluating Transformer-Based Pretrained Models for Classical Arabic Named Entity Recognition", "publication_year": 2025, "publication_date": "2025-01-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Mariam Muhammed", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I145487455", "display_name": "Cairo University", "ror": "https://ror.org/03q21mh05", "country_code": "EG", "type": "education", "lineage": ["https://openalex.org/I145487455"]}], "countries": ["EG"], "is_corresponding": false, "raw_author_name": "Mariam Muhammed", "raw_affiliation_strings": ["Faculty of Graduate Studies for Statistical Research , Cairo University , Egypt"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Faculty of Graduate Studies for Statistical Research , Cairo University , Egypt", "institution_ids": ["https://openalex.org/I145487455"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5056617731", "display_name": "Shahira Shaaban Azab", "orcid": "https://orcid.org/0000-0001-6903-272X", "observed_orcids": ["https://orcid.org/0000-0001-6903-272X"]}, "institutions": [{"id": "https://openalex.org/I145487455", "display_name": "Cairo University", "ror": "https://ror.org/03q21mh05", "country_code": "EG", "type": "education", "lineage": ["https://openalex.org/I145487455"]}], "countries": ["EG"], "is_corresponding": false, "raw_author_name": "Shahira Azab", "raw_affiliation_strings": ["Faculty of Graduate Studies for Statistical Research , Cairo University , Egypt"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Faculty of Graduate Studies for Statistical Research , Cairo University , Egypt", "institution_ids": ["https://openalex.org/I145487455"]}]}], "abstract_inverted_index": {"This": [0], "study": [1, 87, 188], "presents": [2], "a": [3, 213], "comprehensive": [4], "comparative": [5, 150], "evaluation": [6], "of": [7, 33, 38, 128, 197, 223], "transformer-based": [8, 76], "pretrained": [9], "language": [10], "models": [11, 77, 89, 109, 141, 161], "for": [12, 49, 203, 216], "Named": [13], "Entity": [14], "Recognition": [15], "(NER)": [16], "in": [17, 175, 181], "Classical": [18, 50, 132, 183, 205], "Arabic,": [19], "an": [20], "underexplored": [21], "linguistic": [22, 57], "variety": [23], "characterized": [24], "by": [25, 171], "rich": [26], "morphology,": [27], "orthographic": [28], "ambiguity,": [29], "and": [30, 53, 80, 94, 102, 146, 154, 159, 219], "the": [31, 44, 56, 63, 119, 126, 192, 221], "absence": [32], "diacritics.": [34], "The": [35, 86, 104], "main": [36], "objective": [37], "this": [39, 187], "work": [40], "is": [41, 189], "to": [42, 54, 191, 227], "identify": [43], "most": [45], "effective": [46], "transformer": [47], "model": [48, 60], "Arabic": [51, 133, 184, 206], "NER": [52], "analyze": [55], "factors": [58], "influencing": [59], "performance.": [61], "Using": [62], "CANERCorpus,": [64, 193], "which": [65, 194], "contains": [66], "Hadith": [67, 198], "texts": [68], "annotated": [69], "with": [70, 152], "twenty": [71], "fine-grained": [72], "entity": [73], "types,": [74], "ten": [75], "were": [78], "fine-tuned": [79], "evaluated": [81], "under": [82], "consistent": [83], "experimental": [84], "settings.": [85], "benchmarks": [88], "such": [90], "as": [91], "AraBERT,": [92], "ArBERT,": [93], "multiple": [95], "CAMeLBERT": [96], "variants,": [97], "comparing": [98], "their": [99], "precision,": [100], "recall,": [101], "F1-scores.": [103], "results": [105, 200], "demonstrate": [106, 220], "that": [107, 139, 166], "all": [108], "achieve": [110], "strong": [111], "performance": [112], "(F1": [113, 122], ">": [114], "96%),": [115], "while": [116], "CAMeL-CA-NER": [117, 167], "attains": [118], "highest": [120], "score": [121], "=": [123], "97.78%),": [124], "confirming": [125], "advantage": [127], "domain-specific": [129], "pretraining": [130], "on": [131], "data.": [134], "Error": [135], "analysis": [136, 151], "further": [137], "reveals": [138], "domain-adapted": [140], "better": [142], "handle": [143], "ambiguous": [144], "entities": [145], "religious": [147], "terminology.": [148], "A": [149], "traditional": [153], "non-transformer": [155], "approaches,": [156], "including": [157], "rule-based": [158], "BERT-CRF": [160], "from": [162], "previous": [163], "studies,": [164], "shows": [165], "surpasses": [168], "earlier": [169], "methods": [170], "more": [172], "than": [173], "3%": [174], "F1-score,": [176], "highlighting": [177], "its": [178], "superior": [179], "capability": [180], "handling": [182], "text.": [185], "However,": [186], "limited": [190], "primarily": [195], "consists": [196], "texts;": [199], "may": [201], "vary": [202], "other": [204], "genres": [207], "or": [208], "domains.": [209, 231], "These": [210], "findings": [211], "provide": [212], "valuable": [214], "benchmark": [215], "future": [217], "research": [218], "adaptability": [222], "modern": [224], "NLP": [225], "architectures": [226], "linguistically": [228], "complex,": [229], "low-resource": [230]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.001500000013038516, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10601", "display_name": "Handwritten Text Recognition Techniques", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.14569/ijacsa.2025.0161019", "is_oa": true, "landing_page_url": "https://doi.org/10.14569/ijacsa.2025.0161019", "pdf_url": "https://thesai.org/Downloads/Volume16No10/Paper_19-Evaluating_Transformer_Based_Pretrained_Models.pdf", "source": {"id": "https://openalex.org/S23629721", "display_name": "International Journal of Advanced Computer Science and Applications", "issn_l": "2156-5570", "issn": ["2156-5570", "2158-107X"], "is_oa": true, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "norway-1"], "host_organization": "https://openalex.org/P4310311819", "host_organization_name": "Science and Information Organization", "host_organization_lineage": ["https://openalex.org/P4310311819"], "host_organization_lineage_names": ["Science and Information Organization"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Advanced Computer Science and Applications", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4407687439", "doi": "https://doi.org/10.48550/arxiv.2502.10940", "title": "CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation", "publication_year": 2025, "publication_date": "2025-02-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5078128168", "display_name": "Ziyue Liu", "orcid": "https://orcid.org/0000-0002-3246-2301", "observed_orcids": ["https://orcid.org/0000-0002-3246-2301"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Ziyue", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016452826", "display_name": "Ruijie K. Zhang", "orcid": "https://orcid.org/0000-0002-7251-5527", "observed_orcids": ["https://orcid.org/0000-0002-7251-5527"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ruijie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100656202", "display_name": "Zhengyang Wang", "orcid": "https://orcid.org/0000-0002-5146-2884", "observed_orcids": ["https://orcid.org/0000-0002-5146-2884"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Zhengyang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Yan, Mingsong", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yan, Mingsong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101629102", "display_name": "Zi Yang", "orcid": "https://orcid.org/0000-0002-2122-2230", "observed_orcids": ["https://orcid.org/0000-0002-2122-2230"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Zi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067040957", "display_name": "Paul Hovland", "orcid": "https://orcid.org/0000-0002-0907-2567", "observed_orcids": ["https://orcid.org/0000-0002-0907-2567"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hovland, Paul", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085745891", "display_name": "Bogdan Nicolae", "orcid": "https://orcid.org/0000-0002-0661-7509", "observed_orcids": ["https://orcid.org/0000-0002-0661-7509"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nicolae, Bogdan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5046613458", "display_name": "Franck Cappello", "orcid": "https://orcid.org/0000-0002-7890-3934", "observed_orcids": ["https://orcid.org/0000-0002-7890-3934"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cappello, Franck", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Tang, Sui", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tang, Sui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101427338", "display_name": "Zheng Zhang", "orcid": "https://orcid.org/0000-0003-3082-6842", "observed_orcids": ["https://orcid.org/0000-0003-3082-6842"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Zheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"The": [0, 132], "full-size": [1, 51], "MLPs": [2], "and": [3, 43, 71, 76, 100, 129], "the": [4, 28, 68, 94], "projection": [5], "layers": [6, 52], "in": [7, 22], "attention": [8], "introduce": [9], "tremendous": [10], "model": [11, 74], "sizes": [12], "of": [13, 30], "large": [14], "language": [15], "models": [16, 82], "(LLMs),": [17], "consuming": [18], "extensive": [19], "computational": [20], "resources": [21], "pre-training.": [23], "We": [24], "empirically": [25], "observe": [26], "that": [27, 56, 91], "activations": [29, 60], "pre-trained": [31], "LLMs": [32, 133], "exhibit": [33], "low-rank": [34, 59], "property.": [35], "Motivated": [36], "by": [37, 97, 104], "such": [38], "observations,": [39], "we": [40], "propose": [41], "CoLA": [42, 92], "its": [44], "memory-efficient": [45], "implementation,": [46], "CoLA-M,": [47], "to": [48, 86], "replace": [49], "these": [50], "with": [53, 83, 124, 143], "compute-efficient": [54], "auto-encoders": [55], "naturally": [57], "enforce": [58], "throughout": [61], "training.": [62], "This": [63], "fundamental": [64], "architectural": [65], "change": [66], "eliminates": [67], "activation": [69], "redundancy": [70], "significantly": [72], "boosts": [73], "capacity": [75], "training": [77, 102], "efficiency.": [78, 131], "Experiments": [79], "on": [80, 147], "LLaMA": [81], "60": [84], "million": [85], "7": [87], "billion": [88], "parameters": [89], "show": [90], "reduces": [93], "computing": [95], "cost": [96, 116, 146], "$\\bf": [98, 105, 137], "2\\pmb{\\times}$": [99, 138], "improves": [101], "throughput": [103], "1.86\\pmb{\\times}$": [106], "while": [107], "maintaining": [108], "full-rank": [109], "level": [110], "performance.": [111], "CoLA-M": [112], "further": [113], "squeezes": [114], "memory": [115, 130, 145], "without": [117], "sacrificing": [118], "throughput,": [119], "offering": [120], "a": [121], "pre-training": [122], "approach": [123], "collectively": [125], "superior": [126], "parameter,": [127], "computing,": [128], "produced": [134], "are": [135], "also": [136], "smaller,": [139], "enabling": [140], "faster": [141], "inference": [142], "lower": [144], "resource-constrained": [148], "platforms.": [149]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.6518999934196472, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.6518999934196472, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.28780001401901245, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.022199999541044235, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.10940", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.10940", "pdf_url": "https://arxiv.org/pdf/2502.10940", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4410633563", "doi": "https://doi.org/10.1101/2025.05.22.25328162", "title": "Reasoning Over Pre-training: Evaluating LLM Performance and Augmentation in Women\u2019s Health", "publication_year": 2025, "publication_date": "2025-05-23", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5039581278", "display_name": "Martha Imprialou", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Martha Imprialou", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117648075", "display_name": "Nikos Kaltsas", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nikos Kaltsas", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117648076", "display_name": "Viktoriia Oliinyk", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Viktoriia Oliinyk", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117648077", "display_name": "Tom Vigrass", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tom Vigrass", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Joel Schwarzmann", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Joel Schwarzmann", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Rachel Rosenthal", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rachel Rosenthal", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5018391302", "display_name": "Craig A. Glastonbury", "orcid": "https://orcid.org/0000-0001-5542-2225", "observed_orcids": ["https://orcid.org/0000-0001-5542-2225"]}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}, {"id": "https://openalex.org/I4210115812", "display_name": "Human Technopole", "ror": "https://ror.org/029gmnc79", "country_code": "IT", "type": "facility", "lineage": ["https://openalex.org/I4210115812"]}], "countries": ["GB", "IT"], "is_corresponding": false, "raw_author_name": "Craig Glastonbury", "raw_affiliation_strings": ["Nuffield Department of Medicine", "Human Technopole, Viale Rita Levi-Montalcini 1, 20157, Milan, Italy", "Nuffield Department of Medicine, University of Oxford", "Oxford, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nuffield Department of Medicine", "institution_ids": []}, {"raw_affiliation_string": "Human Technopole, Viale Rita Levi-Montalcini 1, 20157, Milan, Italy", "institution_ids": ["https://openalex.org/I4210115812"]}, {"raw_affiliation_string": "Nuffield Department of Medicine, University of Oxford", "institution_ids": ["https://openalex.org/I40120149"]}, {"raw_affiliation_string": "Oxford, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Chris Wigley", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chris Wigley", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Matt Gillam", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Matt Gillam", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5069964021", "display_name": "Nikita Kanani", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nikita Kanani", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5053270946", "display_name": "Prasanna Raj Supramaniam", "orcid": "https://orcid.org/0000-0001-5969-0243", "observed_orcids": ["https://orcid.org/0000-0001-5969-0243"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pras Supramaniam", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065124380", "display_name": "Ingrid Granne", "orcid": "https://orcid.org/0000-0002-7056-5723", "observed_orcids": ["https://orcid.org/0000-0002-7056-5723"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ingrid Granne", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048738826", "display_name": "Cecilia M. Lindgren", "orcid": "https://orcid.org/0000-0002-4903-9374", "observed_orcids": ["https://orcid.org/0000-0002-4903-9374"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Cecilia M. Lindgren", "raw_affiliation_strings": ["Aneira Health;", "Aneira Health, London, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Aneira Health;", "institution_ids": []}, {"raw_affiliation_string": "Aneira Health, London, United Kingdom", "institution_ids": []}]}], "abstract_inverted_index": {"Abstract": [0], "Recent": [1], "advances": [2], "in": [3, 10, 16, 127], "large": [4], "language": [5], "models": [6, 106, 110], "(LLMs)": [7], "show": [8], "promise": [9], "clinical": [11, 56, 121], "applications,": [12], "but": [13], "their": [14], "performance": [15, 119], "women\u2019s": [17], "health": [18], "remains": [19], "underexamined": [20], "1": [21, 102], ".": [22, 103, 115, 161], "We": [23, 116], "evaluated": [24], "LLMs": [25], "on": [26, 89, 95], "2,337": [27], "questions": [28], "from": [29, 35, 60, 67], "obstetrics": [30], "and": [31, 41, 58, 93, 123, 132, 146, 158], "gynaecology,": [32], "including": [33], "1,392": [34], "the": [36, 68, 138, 148], "Royal": [37], "College": [38], "of": [39, 54, 140, 150], "Obstetricians": [40], "Gynaecologists": [42], "Part": [43, 47, 91], "2": [44, 49, 92], "examination": [45], "(MRCOG": [46], "2)": [48], ",": [50, 63], "a": [51, 64], "UK-based": [52], "test": [53], "advanced": [55], "decision-making,": [57], "945": [59], "MedQA": [61], "3": [62], "dataset": [65], "derived": [66], "United": [69], "States": [70], "Medical": [71], "Licensing": [72], "Examination": [73], "(USMLE).": [74], "The": [75], "best-performing": [76], "model\u2014OpenAI\u2019s": [77], "o1-preview": [78], "4": [79], "enhanced": [80], "with": [81], "retrieval-augmented": [82], "generation": [83], "(RAG)": [84], "5,6": [85], "\u2014achieved": [86], "72.00%": [87], "accuracy": [88, 126, 157], "MRCOG": [90], "92.30%": [94], "MedQA,": [96], "exceeding": [97], "prior": [98], "benchmarks": [99], "by": [100, 120], "21.6%": [101], "General-purpose": [104], "reasoning": [105, 141], "outperformed": [107], "domain-specific": [108, 144], "fine-tuned": [109], "such": [111], "as": [112], "MED-LM": [113], "7": [114], "also": [117], "analyse": [118], "subdomain": [122], "discover": [124], "lower": [125], "areas": [128], "like": [129, 153], "fetal": [130], "medicine": [131], "postpartum": [133], "care.": [134], "These": [135], "findings": [136], "highlight": [137], "importance": [139], "capabilities": [142], "over": [143], "fine-tuning": [145], "demonstrate": [147], "value": [149], "augmentation": [151], "methods": [152], "RAG": [154], "for": [155], "improving": [156], "interpretability": [159], "8": [160]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9926999807357788, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9926999807357788, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.003599999938160181, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0017000000225380063, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1101/2025.05.22.25328162", "is_oa": true, "landing_page_url": "https://doi.org/10.1101/2025.05.22.25328162", "pdf_url": "https://www.medrxiv.org/content/medrxiv/early/2025/05/23/2025.05.22.25328162.full.pdf", "source": {"id": "https://openalex.org/S3005729997", "display_name": "medRxiv", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core"], "host_organization": null, "host_organization_name": null, "host_organization_lineage": ["https://openalex.org/P4310315909"], "host_organization_lineage_names": ["Cold Spring Harbor Laboratory Press"], "type": "repository"}, "license": null, "license_id": null, "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": "medRxiv", "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416052279", "doi": "https://doi.org/10.48550/arxiv.2504.10917", "title": "Towards A Universal Graph Structural Encoder", "publication_year": 2025, "publication_date": "2025-04-15", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100339552", "display_name": "Jialin Chen", "orcid": "https://orcid.org/0009-0007-0909-4620", "observed_orcids": ["https://orcid.org/0009-0007-0909-4620"]}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Chen, Jialin", "raw_affiliation_strings": ["Department of Computer Science , Yale University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Yale University", "institution_ids": ["https://openalex.org/I32971472"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079395336", "display_name": "Haolan Zuo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Zuo, Haolan", "raw_affiliation_strings": ["Department of Computer Science , Yale University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Yale University", "institution_ids": ["https://openalex.org/I32971472"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100427170", "display_name": "Haoyu Wang", "orcid": "https://orcid.org/0000-0001-6647-598X", "observed_orcids": ["https://orcid.org/0000-0001-6647-598X", "https://orcid.org/0000-0003-3131-8217"]}, "institutions": [{"id": "https://openalex.org/I130701444", "display_name": "Georgia Institute of Technology", "ror": "https://ror.org/01zkghx44", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130701444"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Wang, Haoyu Peter", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering , Geor- gia Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering , Geor- gia Institute of Technology", "institution_ids": ["https://openalex.org/I130701444"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052694295", "display_name": "Siqi Miao", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I130701444", "display_name": "Georgia Institute of Technology", "ror": "https://ror.org/01zkghx44", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130701444"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Miao, Siqi", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering , Geor- gia Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering , Geor- gia Institute of Technology", "institution_ids": ["https://openalex.org/I130701444"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100455171", "display_name": "Pan Li", "orcid": "https://orcid.org/0000-0001-6522-2446", "observed_orcids": ["https://orcid.org/0000-0001-6522-2446", "https://orcid.org/0009-0007-2106-9559", "https://orcid.org/0000-0002-8391-6510"]}, "institutions": [{"id": "https://openalex.org/I130701444", "display_name": "Georgia Institute of Technology", "ror": "https://ror.org/01zkghx44", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I130701444"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Li, Pan", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering , Geor- gia Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering , Geor- gia Institute of Technology", "institution_ids": ["https://openalex.org/I130701444"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5078337825", "display_name": "Rex Ying", "orcid": "https://orcid.org/0000-0002-5856-5229", "observed_orcids": ["https://orcid.org/0000-0002-5856-5229"]}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ying, Rex", "raw_affiliation_strings": ["Department of Computer Science , Yale University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Yale University", "institution_ids": ["https://openalex.org/I32971472"]}]}], "abstract_inverted_index": {"Recent": [0], "advancements": [1], "in": [2, 38], "large-scale": [3], "pre-training": [4], "have": [5], "shown": [6], "the": [7, 17, 35, 68, 80, 107, 117, 210], "potential": [8], "to": [9, 34, 66, 76, 97, 145, 207], "learn": [10], "generalizable": [11], "representations": [12], "for": [13, 169, 186, 194], "downstream": [14, 178], "tasks.": [15], "In": [16], "graph": [18, 28, 39, 73, 81, 94, 120, 140, 155, 179, 183], "domain,": [19], "however,": [20], "capturing": [21], "and": [22, 112, 149, 162, 166, 189, 201], "transferring": [23], "structural": [24, 100, 121, 141, 167], "information": [25], "across": [26, 42, 102], "different": [27, 53], "domains": [29, 104], "remains": [30], "challenging,": [31], "primarily": [32], "due": [33], "inherent": [36], "differences": [37], "topological": [40, 70, 151], "patterns": [41, 101], "various": [43, 177], "contexts.": [44], "For": [45], "example,": [46], "a": [47, 57, 91, 131], "social": [48, 110], "network's": [49], "structure": [50], "is": [51, 116], "fundamentally": [52], "from": [54], "that": [55], "of": [56, 72, 79], "product": [58], "co-purchase": [59], "graph.": [60], "Additionally,": [61], "most": [62], "existing": [63], "models": [64], "struggle": [65], "capture": [67, 98], "rich": [69], "complexity": [71], "structures,": [74], "leading": [75], "inadequate": [77], "exploration": [78], "embedding": [82], "space.": [83], "To": [84], "address": [85], "these": [86], "challenges,": [87], "we": [88], "propose": [89], "GFSE,": [90], "universal": [92], "pre-trained": [93, 123, 158], "encoder": [95, 122], "designed": [96], "transferable": [99], "diverse": [103], "such": [105], "as": [106], "web": [108], "graph,": [109], "networks,": [111], "citation": [113], "networks.": [114], "GFSE": [115, 134, 159], "first": [118], "cross-domain": [119], "with": [124, 176], "multiple": [125], "self-supervised": [126], "learning": [127], "objectives.": [128], "Built": [129], "on": [130, 199], "Graph": [132], "Transformer,": [133], "incorporates": [135], "attention": [136], "mechanisms": [137], "informed": [138], "by": [139], "information,": [142], "enabling": [143], "it": [144], "encode": [146], "intricate": [147], "multi-level": [148], "fine-grained": [150], "features": [152, 188], "within": [153], "complex": [154], "structures.": [156], "The": [157], "produces": [160], "generic": [161], "theoretically": [163], "expressive": [164], "positional": [165], "encoding": [168], "graphs,": [170], "which": [171], "can": [172], "be": [173], "seamlessly": [174], "integrated": [175], "feature": [180], "encoders,": [181], "including": [182], "neural": [184], "networks": [185], "vectorized": [187], "Large": [190], "Language": [191], "Models": [192], "(LLMs)": [193], "text-attributed": [195], "graphs.": [196], "Comprehensive": [197], "experiments": [198], "synthetic": [200], "real-world": [202], "datasets": [203], "demonstrate": [204], "GFSE's": [205], "capability": [206], "significantly": [208], "enhance": [209], "model's": [211], "performance": [212], "while": [213], "requiring": [214], "substantially": [215], "less": [216], "task-specific": [217], "fine-tuning.": [218]}, "primary_topic": {"id": "https://openalex.org/T11273", "display_name": "Advanced Graph Neural Networks", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11273", "display_name": "Advanced Graph Neural Networks", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12292", "display_name": "Graph Theory and Algorithms", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10064", "display_name": "Complex Network Analysis Techniques", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/3109", "display_name": "Statistical and Nonlinear Physics"}, "field": {"id": "https://openalex.org/fields/31", "display_name": "Physics and Astronomy"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.10917", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.10917", "pdf_url": "https://arxiv.org/pdf/2504.10917", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4413010596", "doi": "https://doi.org/10.1371/journal.pone.0325531", "title": "Bag-of-words is competitive with sum-of-embeddings language-inspired representations on protein inference", "publication_year": 2025, "publication_date": "2025-08-06", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5040179655", "display_name": "Frixos Papadopoulos", "orcid": "https://orcid.org/0000-0002-4429-1562", "observed_orcids": ["https://orcid.org/0000-0002-4429-1562"]}, "institutions": [{"id": "https://openalex.org/I43439940", "display_name": "University of Southampton", "ror": "https://ror.org/01ryk1543", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I43439940"]}], "countries": ["GB"], "is_corresponding": true, "raw_author_name": "Frixos Papadopoulos", "raw_affiliation_strings": ["Vision-Learning-Control Group, Department of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, United Kingdom"], "raw_orcid": "https://orcid.org/0000-0002-4429-1562", "affiliations": [{"raw_affiliation_string": "Vision-Learning-Control Group, Department of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, United Kingdom", "institution_ids": ["https://openalex.org/I43439940"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085481160", "display_name": "Tilman S\u00e1nchez-Elsner", "orcid": "https://orcid.org/0000-0003-1915-2410", "observed_orcids": ["https://orcid.org/0000-0003-1915-2410"]}, "institutions": [{"id": "https://openalex.org/I43439940", "display_name": "University of Southampton", "ror": "https://ror.org/01ryk1543", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I43439940"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Tilman Sanchez-Elsner", "raw_affiliation_strings": ["Clinical and Experimental Sciences, Department of Medicine, University of Southampton, Southampton, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Clinical and Experimental Sciences, Department of Medicine, University of Southampton, Southampton, United Kingdom", "institution_ids": ["https://openalex.org/I43439940"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5033579333", "display_name": "Mahesan Niranjan", "orcid": "https://orcid.org/0000-0001-7021-140X", "observed_orcids": ["https://orcid.org/0000-0001-7021-140X"]}, "institutions": [{"id": "https://openalex.org/I43439940", "display_name": "University of Southampton", "ror": "https://ror.org/01ryk1543", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I43439940"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Mahesan Niranjan", "raw_affiliation_strings": ["Vision-Learning-Control Group, Department of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Vision-Learning-Control Group, Department of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, United Kingdom", "institution_ids": ["https://openalex.org/I43439940"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5044496336", "display_name": "Ashley Heinson", "orcid": "https://orcid.org/0000-0001-8695-6203", "observed_orcids": ["https://orcid.org/0000-0001-8695-6203"]}, "institutions": [{"id": "https://openalex.org/I43439940", "display_name": "University of Southampton", "ror": "https://ror.org/01ryk1543", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I43439940"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Ashley I. Heinson", "raw_affiliation_strings": ["Clinical Informatics Research Unit, Cancer Sciences, Department of Medicine, University of Southampton, Southampton, United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Clinical Informatics Research Unit, Cancer Sciences, Department of Medicine, University of Southampton, Southampton, United Kingdom", "institution_ids": ["https://openalex.org/I43439940"]}]}], "abstract_inverted_index": {"Inferring": [0], "protein": [1, 23, 64, 103, 112, 116, 143, 176], "function": [2, 163], "is": [3, 31], "a": [4, 110], "fundamental": [5], "and": [6, 19, 56, 142, 178], "long-standing": [7], "problem": [8], "in": [9, 13, 35, 43, 125], "biology.": [10], "Laboratory": [11], "experiments": [12], "this": [14, 95], "field": [15], "are": [16], "often": [17], "expensive,": [18], "therefore": [20], "large-scale": [21], "computational": [22], "inference": [24, 117, 144], "from": [25, 52, 80, 196], "readily": [26], "available": [27], "amino": [28], "acid": [29], "sequences": [30], "needed": [32], "to": [33, 59], "understand": [34], "more": [36, 192], "detail": [37], "the": [38, 68, 85, 99, 126, 152, 181, 197], "mechanisms": [39], "underlying": [40], "biological": [41, 194], "processes": [42], "living": [44], "organisms.": [45], "Recently,": [46], "studies": [47], "have": [48, 168], "utilised": [49], "mathematical": [50], "ideas": [51], "natural": [53], "language": [54, 71], "processing": [55], "self-supervised": [57, 81, 107, 137, 172], "learning,": [58, 138], "derive": [60], "features": [61, 155], "based": [62, 135], "on": [63, 109, 114, 136, 139, 175], "sequence": [65, 140, 198], "information.": [66], "In": [67, 94], "area": [69], "of": [70, 88, 101, 128, 183], "modelling,": [72], "it": [73], "has": [74], "been": [75], "shown": [76], "that": [77, 121, 151, 190], "learnt": [78, 105], "representations": [79, 104, 124, 189], "pre-training": [82, 108, 185], "can": [83], "capture": [84, 158, 191], "semantic": [86], "information": [87, 160, 195], "words": [89], "well": [90], "for": [91, 161, 171, 187], "downstream": [92], "applications.": [93], "study,": [96], "we": [97, 149], "tested": [98], "ability": [100], "sequence-based": [102], "using": [106], "large": [111], "database,": [113], "multiple": [115], "tasks.": [118, 145], "We": [119], "show": [120, 150], "simple": [122], "baseline": [123], "form": [127], "bag-of-words": [129, 157], "histograms": [130], "perform": [131], "better": [132], "than": [133], "those": [134], "similarity": [141], "By": [146], "feature": [147], "selection": [148], "top": [153], "discriminant": [154], "help": [156], "important": [159, 169], "data-driven": [162], "prediction.": [164], "These": [165], "findings": [166], "could": [167], "implications": [170], "learning": [173, 188], "models": [174], "sequences,": [177], "might": [179], "encourage": [180], "consideration": [182], "alternative": [184], "schemes": [186], "meaningful": [193], "alone.": [199]}, "primary_topic": {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.989300012588501, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.989300012588501, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10887", "display_name": "Bioinformatics and Genomic Networks", "score": 0.0031999999191612005, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10044", "display_name": "Protein Structure and Dynamics", "score": 0.002899999963119626, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "doi:10.1371/journal.pone.0325531", "is_oa": true, "landing_page_url": "https://doi.org/10.1371/journal.pone.0325531", "pdf_url": null, "source": {"id": "https://openalex.org/S202381698", "display_name": "PLoS ONE", "issn_l": "1932-6203", "issn": ["1932-6203"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "doyens", "erih-plus", "jufo-1", "ki-jl-1", "medline", "norway-1"], "host_organization": "https://openalex.org/P4310315706", "host_organization_name": "Public Library of Science", "host_organization_lineage": ["https://openalex.org/P4310315706"], "host_organization_lineage_names": ["Public Library of Science"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "PLOS One", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4410128284", "doi": "https://doi.org/10.2139/ssrn.5242694", "title": "Beyond Kv Caching: Shared Attention for Efficient Llms", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5057076890", "display_name": "Bingli Liao", "orcid": "https://orcid.org/0009-0005-0474-7464", "observed_orcids": ["https://orcid.org/0009-0005-0474-7464"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Bingli Liao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5028815763", "display_name": "Danilo Vasconcellos Vargas", "orcid": "https://orcid.org/0000-0001-7442-1279", "observed_orcids": ["https://orcid.org/0000-0001-7442-1279"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Danilo  Vasconcellos Vargas", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5663999915122986, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5663999915122986, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.1770000010728836, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.17499999701976776, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.2139/ssrn.5242694", "is_oa": true, "landing_page_url": "https://doi.org/10.2139/ssrn.5242694", "pdf_url": null, "source": {"id": "https://openalex.org/S4210172589", "display_name": "SSRN Electronic Journal", "issn_l": "1556-5068", "issn": ["1556-5068"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I1318003438", "host_organization_name": "RELX Group (Netherlands)", "host_organization_lineage": ["https://openalex.org/I1318003438"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 3, "is_retracted": false}, {"id": "https://openalex.org/W7129042851", "doi": "https://doi.org/10.71448/bcds2561-3", "title": "Self-Supervised Code-Mixed Representation Learning for Multi-Label Emoji, Sentiment, and Emotion Prediction", "publication_year": 2025, "publication_date": "2025-03-30", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5109746696", "display_name": "Asif Shehzad", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Asif Shehzad", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5126123901", "display_name": "Rahul Sharma", "orcid": "https://orcid.org/0000-0003-0366-047X", "observed_orcids": ["https://orcid.org/0000-0003-0366-047X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rahul Sharma", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5065100828", "display_name": "Pushpak Bhattacharyya", "orcid": "https://orcid.org/0000-0001-5319-5508", "observed_orcids": ["https://orcid.org/0000-0001-5319-5508"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pushpak Bhattacharyya", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Emoji": [0], "usage": [1], "and": [2, 19, 22, 38, 48, 58, 73, 82, 131, 152, 174, 194, 213, 216, 225, 239], "code-mixed": [3, 26, 62, 103, 117, 163, 205, 237], "language": [4, 84, 129], "have": [5], "become": [6], "central": [7], "to": [8, 33, 186, 210], "informal": [9], "online": [10], "communication,": [11], "especially": [12], "in": [13, 80, 139], "multilingual": [14, 108, 176], "communities.": [15], "Predicting": [16], "suitable": [17], "emojis": [18], "inferring": [20], "sentiment": [21, 150], "emotion": [23, 59, 155], "from": [24, 106], "noisy,": [25], "social": [27, 118], "media": [28, 119], "text": [29], "is": [30], "challenging": [31], "due": [32], "non-standard": [34], "spelling,": [35], "cross-script": [36], "mixing,": [37], "strong": [39, 175], "pragmatic": [40], "effects.": [41], "Prior": [42], "work": [43, 246], "has": [44], "proposed": [45], "specialized": [46, 100], "encoders": [47], "multi-task": [49, 141], "frameworks": [50], "for": [51, 101, 143, 181, 236, 244], "joint": [52], "prediction": [53, 183], "of": [54, 161, 232], "multi-label": [55, 145], "emojis,": [56, 223], "sentiment,": [57, 224], "on": [60, 69, 114, 157, 247], "English\u2013Hindi": [61, 162], "tweets.": [63, 164], "However,": [64], "these": [65], "approaches": [66], "are": [67], "built": [68], "relatively": [70], "shallow": [71], "architectures": [72, 173], "do": [74], "not": [75], "fully": [76], "exploit": [77], "recent": [78], "advances": [79], "self-supervised": [81, 97, 204, 234], "large": [83], "model": [85, 99], "(LLM)": [86], "based": [87], "representation": [88], "learning.": [89, 134], "In": [90], "this": [91], "paper,": [92], "we": [93, 111], "introduce": [94], "CodeMixLM,": [95], "a": [96, 107, 140, 241], "transformer": [98, 109, 177], "Hinglish": [102], "text.": [104], "Starting": [105], "backbone,": [110], "continue": [112], "pretraining": [113, 206], "large-scale": [115], "unlabeled": [116], "data": [120], "with": [121], "three": [122], "auxiliary": [123], "objectives:": [124], "masked": [125], "span": [126], "denoising,": [127], "script-aware": [128], "identification,": [130], "emoji-aware": [132, 248], "contrastive": [133], "We": [135], "then": [136], "fine-tune": [137], "CodeMixLM": [138, 168], "setting": [142], "(i)": [144], "emoji": [146, 182], "prediction,": [147], "(ii)": [148], "three-way": [149], "classification,": [151], "(iii)": [153], "seven-way": [154], "classification": [156], "the": [158, 220, 230], "SENTIMOJI": [159], "dataset": [160], "Across": [165], "all": [166], "tasks,": [167], "substantially": [169], "outperforms": [170], "prior": [171], "task-specific": [172], "baselines,": [178], "improving": [179], "macro-F1": [180], "by": [184], "up": [185], "several": [187], "points": [188], "while": [189], "also": [190], "yielding": [191], "better": [192, 218], "calibration": [193], "label": [195], "efficiency": [196], "under": [197], "reduced": [198], "supervision.": [199], "Detailed": [200], "analyses": [201], "show": [202], "that": [203], "(1)": [207], "improves": [208], "robustness": [209], "spelling": [211], "variants": [212], "code-switching": [214], "patterns,": [215], "(2)": [217], "captures": [219], "interaction": [221], "between": [222], "emotion.": [226], "Our": [227], "results": [228], "highlight": [229], "importance": [231], "domain-specialized": [233], "learning": [235], "NLP": [238], "offer": [240], "stronger": [242], "baseline": [243], "future": [245], "affective": [249], "computing.": [250]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9375, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9375, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.030700000002980232, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13155", "display_name": "Digital Communication and Language", "score": 0.013399999588727951, "subfield": {"id": "https://openalex.org/subfields/1709", "display_name": "Human-Computer Interaction"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.71448/bcds2561-3", "is_oa": true, "landing_page_url": "https://doi.org/10.71448/bcds2561-3", "pdf_url": null, "source": {"id": "https://openalex.org/S7407053757", "display_name": "Bulletin of Computer and Data Sciences", "issn_l": "3072-2926", "issn": ["3072-2926"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Bulletin of Computer and Data Sciences", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416237322", "doi": "https://doi.org/10.48550/arxiv.2511.09540", "title": "vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs", "publication_year": 2025, "publication_date": "2025-11-12", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Shao, Minye", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I190082696", "display_name": "Durham University", "ror": "https://ror.org/01v29qb04", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I190082696"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Shao, Minye", "raw_affiliation_strings": ["Department of Computer Science , Durham University , Durham , UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Durham University , Durham , UK", "institution_ids": ["https://openalex.org/I190082696"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Guo, Sihan", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I190082696", "display_name": "Durham University", "ror": "https://ror.org/01v29qb04", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I190082696"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Guo, Sihan", "raw_affiliation_strings": ["Department of Computer Science , Durham University , Durham , UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Durham University , Durham , UK", "institution_ids": ["https://openalex.org/I190082696"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Li, Xinrun", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I190082696", "display_name": "Durham University", "ror": "https://ror.org/01v29qb04", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I190082696"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Li, Xinrun", "raw_affiliation_strings": ["Department of Computer Science , Durham University , Durham , UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Durham University , Durham , UK", "institution_ids": ["https://openalex.org/I190082696"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082537614", "display_name": "Xingyu Miao", "orcid": "https://orcid.org/0000-0003-1203-8279", "observed_orcids": ["https://orcid.org/0000-0003-1203-8279"]}, "institutions": [{"id": "https://openalex.org/I190082696", "display_name": "Durham University", "ror": "https://ror.org/01v29qb04", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I190082696"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Miao, Xingyu", "raw_affiliation_strings": ["Department of Computer Science , Durham University , Durham , UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Durham University , Durham , UK", "institution_ids": ["https://openalex.org/I190082696"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5083020611", "display_name": "Haoran Duan", "orcid": "https://orcid.org/0000-0001-9956-7020", "observed_orcids": ["https://orcid.org/0000-0001-9956-7020"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Duan, Haoran", "raw_affiliation_strings": ["Department of Automation , Tsinghua University , Beijing , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation , Tsinghua University , Beijing , China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100694199", "display_name": "Yang Long", "orcid": "https://orcid.org/0000-0002-6281-6043", "observed_orcids": ["https://orcid.org/0000-0002-6281-6043"]}, "institutions": [{"id": "https://openalex.org/I190082696", "display_name": "Durham University", "ror": "https://ror.org/01v29qb04", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I190082696"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Long, Yang", "raw_affiliation_strings": ["Department of Computer Science , Durham University , Durham , UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science , Durham University , Durham , UK", "institution_ids": ["https://openalex.org/I190082696"]}]}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 36, 95, 146, 169], "context": [3, 38], "optimization": [4, 76], "(CoOp)": [5], "guided": [6], "by": [7, 41], "large": [8], "language": [9], "model": [10, 55, 81], "(LLM)-distilled": [11], "medical": [12, 156, 159], "semantic": [13, 42, 124], "priors": [14], "offer": [15], "a": [16, 109, 119], "scalable": [17], "alternative": [18], "to": [19, 50, 80, 91, 136, 178, 181, 192], "manual": [20], "prompt": [21, 34], "engineering": [22], "and": [23, 46, 54, 99, 129, 141, 162, 172, 186], "full": [24], "fine-tuning": [25], "for": [26], "adapting": [27], "biomedical": [28, 97, 139], "CLIP-based": [29], "vision-language": [30], "models": [31], "(VLMs).": [32], "However,": [33], "learning": [35], "this": [37, 104], "is": [39], "challenged": [40], "misalignment": [43], "between": [44, 126], "LLMs": [45, 128], "CLIP": [47, 130], "variants": [48], "due": [49], "divergent": [51], "training": [52], "corpora": [53], "architectures;": [56], "it": [57], "further": [58], "lacks": [59, 77], "scalability": [60], "across": [61, 154], "continuously": [62, 179], "evolving": [63], "families": [64], "of": [65], "foundation": [66], "models.": [67], "More": [68], "critically,": [69], "pairwise": [70], "multimodal": [71], "alignment": [72], "via": [73, 132], "conventional": [74], "Euclidean-space": [75], "the": [78, 187], "capacity": [79], "unified": [82], "representations": [83], "or": [84], "apply": [85], "localized": [86], "geometric": [87], "constraints,": [88, 149], "which": [89], "tends": [90], "amplify": [92], "modality": [93], "gaps": [94], "complex": [96], "imaging": [98, 160], "destabilize": [100], "few-shot": [101, 143], "adaptation.": [102], "In": [103], "work,": [105], "we": [106], "propose": [107], "vMFCoOp,": [108], "framework": [110], "that": [111], "inversely": [112], "estimates": [113], "von": [114], "Mises-Fisher": [115], "(vMF)": [116], "distributions": [117], "on": [118], "shared": [120, 194], "Hyperspherical": [121], "Manifold,": [122], "aligning": [123], "biases": [125], "arbitrary": [127], "backbones": [131], "Unified": [133], "Semantic": [134], "Anchors": [135], "achieve": [137], "robust": [138], "prompting": [140], "superior": [142], "classification.": [144], "Grounded": [145], "three": [147], "complementary": [148], "vMFCoOp": [150], "demonstrates": [151], "consistent": [152], "improvements": [153], "14": [155], "datasets,": [157], "12": [158], "modalities,": [161], "13": [163], "anatomical": [164], "regions,": [165], "outperforming": [166], "state-of-the-art": [167], "methods": [168], "accuracy,": [170], "generalization,": [171], "clinical": [173], "applicability.": [174], "This": [175], "work": [176], "aims": [177], "expand": [180], "encompass": [182], "more": [183], "downstream": [184], "applications,": [185], "corresponding": [188], "resources": [189], "are": [190], "intended": [191], "be": [193], "through": [195], "https://github.com/VinyehShaw/UniEqui.": [196]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9326000213623047, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9326000213623047, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.06449999660253525, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.0008999999845400453, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.09540", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.09540", "pdf_url": "https://arxiv.org/pdf/2511.09540", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "other-oa", "license_id": "https://openalex.org/licenses/other-oa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416241498", "doi": "https://doi.org/10.48550/arxiv.2511.08567", "title": "The Path Not Taken: RLVR Provably Learns Off the Principals", "publication_year": 2025, "publication_date": "2025-11-11", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5031867835", "display_name": "Hanqing Zhu", "orcid": "https://orcid.org/0000-0002-2752-6753", "observed_orcids": ["https://orcid.org/0000-0002-2752-6753"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhu, Hanqing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100389531", "display_name": "Zhenyu Zhang", "orcid": "https://orcid.org/0000-0002-5200-3516", "observed_orcids": ["https://orcid.org/0000-0002-5200-3516", "https://orcid.org/0000-0003-0754-3676"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Zhenyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5110397904", "display_name": "Hanxian Huang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Huang, Hanxian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5041890767", "display_name": "DiJia Su", "orcid": "https://orcid.org/0000-0001-9369-4715", "observed_orcids": ["https://orcid.org/0000-0001-9369-4715"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Su, DiJia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085241696", "display_name": "Zechun Liu", "orcid": "https://orcid.org/0000-0001-5856-2506", "observed_orcids": ["https://orcid.org/0000-0001-5856-2506"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Zechun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhao, Jiawei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Jiawei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5056063665", "display_name": "Igor Fedorov", "orcid": "https://orcid.org/0000-0002-7235-4823", "observed_orcids": ["https://orcid.org/0000-0002-7235-4823"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fedorov, Igor", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5031860916", "display_name": "Hamed Pirsiavash", "orcid": "https://orcid.org/0000-0002-2528-3305", "observed_orcids": ["https://orcid.org/0000-0002-2528-3305"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pirsiavash, Hamed", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5110738653", "display_name": "Zhizhou Sha", "orcid": "https://orcid.org/0009-0004-2494-1945", "observed_orcids": ["https://orcid.org/0009-0004-2494-1945"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sha, Zhizhou", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Lee, Jinwon", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lee, Jinwon", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5011883763", "display_name": "David Zhigang Pan", "orcid": "https://orcid.org/0000-0002-5705-2501", "observed_orcids": ["https://orcid.org/0000-0002-5705-2501"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pan, David Z.", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Wang, Zhangyang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Zhangyang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5106668475", "display_name": "Yuandong Tian", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tian, Yuandong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5034622870", "display_name": "Kai Sheng Tai", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tai, Kai Sheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Reinforcement": [0], "Learning": [1], "with": [2, 72], "Verifiable": [3], "Rewards": [4], "(RLVR)": [5], "reliably": [6], "improves": [7], "the": [8, 89, 108, 121, 160, 170, 236], "reasoning": [9], "performance": [10], "of": [11, 24, 38, 128, 174, 233, 238], "large": [12], "language": [13], "models,": [14], "yet": [15], "it": [16], "appears": [17], "to": [18, 51, 62], "modify": [19], "only": [20], "a": [21, 35, 39, 44, 73, 81, 125, 192, 227, 230], "small": [22], "fraction": [23], "parameters.": [25], "We": [26, 67, 114, 222], "revisit": [27], "this": [28, 117, 224], "paradox": [29], "and": [30, 59, 64, 98, 149, 162, 219, 235], "show": [31, 187], "that": [32, 188], "sparsity": [33], "is": [34], "surface": [36], "artifact": [37], "model-conditioned": [40], "optimization": [41, 194], "bias:": [42], "for": [43, 120], "fixed": [45], "pretrained": [46], "model,": [47], "updates": [48], "consistently": [49], "localize": [50], "preferred": [52], "parameter": [53], "regions,": [54, 106], "highly": [55], "consistent": [56], "across": [57], "runs": [58], "largely": [60], "invariant": [61], "datasets": [63], "RL": [65, 189], "recipes.": [66], "mechanistically": [68], "explain": [69], "these": [70, 167], "dynamics": [71], "Three-Gate": [74], "Theory:": [75], "Gate": [76, 84, 99], "I": [77], "(KL": [78], "Anchor)": [79], "imposes": [80], "KL-constrained": [82], "update;": [83], "II": [85], "(Model": [86], "Geometry)": [87], "steers": [88], "step": [90], "off": [91, 134], "principal": [92, 135, 157], "directions": [93, 136], "into": [94], "low-curvature,": [95], "spectrum-preserving": [96], "subspaces;": [97], "III": [100], "(Precision)": [101], "hides": [102], "micro-updates": [103], "in": [104, 137, 181, 191], "non-preferred": [105], "making": [107], "off-principal": [109, 150], "bias": [110], "appear": [111], "as": [112, 209], "sparsity.": [113], "then": [115], "validate": [116], "theory": [118], "and,": [119], "first": [122, 171], "time,": [123], "provide": [124, 169], "parameter-level": [126], "characterization": [127], "RLVR's": [129, 175], "learning": [130, 241], "dynamics:": [131], "RLVR": [132, 234], "learns": [133], "weight": [138], "space,": [139], "achieving": [140], "gains": [141], "via": [142], "minimal": [143], "spectral": [144], "drift,": [145], "reduced": [146], "principal-subspace": [147], "rotation,": [148], "update": [151], "alignment.": [152], "In": [153], "contrast,": [154], "SFT": [155], "targets": [156], "weights,": [158], "distorts": [159], "spectrum,": [161], "even": [163], "lags": [164], "RLVR.": [165], "Together,": [166], "results": [168], "parameter-space": [172], "account": [173], "training": [176], "dynamics,": [177], "revealing": [178], "clear": [179], "regularities": [180], "how": [182], "parameters": [183], "evolve.": [184], "Crucially,": [185], "we": [186], "operates": [190], "distinct": [193], "regime": [195], "from": [196], "SFT,": [197], "so": [198], "directly": [199], "adapting": [200], "SFT-era": [201, 246], "parameter-efficient": [202], "fine-tuning": [203, 218], "(PEFT)": [204], "methods": [205], "can": [206], "be": [207], "flawed,": [208], "evidenced": [210], "by": [211], "our": [212], "case": [213], "studies": [214], "on": [215], "advanced": [216], "sparse": [217], "LoRA": [220], "variants.": [221], "hope": [223], "work": [225], "charts": [226], "path": [228], "toward": [229], "white-box": [231], "understanding": [232], "design": [237], "geometry-aware,": [239], "RLVR-native": [240], "algorithms,": [242], "rather": [243], "than": [244], "repurposed": [245], "heuristics.": [247]}, "primary_topic": {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.4332999885082245, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.4332999885082245, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.24379999935626984, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.1655000001192093, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.08567", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.08567", "pdf_url": "https://arxiv.org/pdf/2511.08567", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4410065220", "doi": "https://doi.org/10.1016/j.eswa.2025.127956", "title": "Crisis impact extraction language model using transformer-based synergy via transfer learning", "publication_year": 2025, "publication_date": "2025-05-04", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5089847954", "display_name": "Seung Ho Woo", "orcid": "https://orcid.org/0000-0001-9839-8616", "observed_orcids": ["https://orcid.org/0000-0001-9839-8616"]}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Seung Ho Woo", "raw_affiliation_strings": ["Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Seonho Woo", "orcid": "https://orcid.org/0009-0006-8041-6701", "observed_orcids": ["https://orcid.org/0009-0006-8041-6701"]}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Seonho Woo", "raw_affiliation_strings": ["Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA"], "raw_orcid": "https://orcid.org/0009-0006-8041-6701", "affiliations": [{"raw_affiliation_string": "Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5021741380", "display_name": "Young\u2010Jun Son", "orcid": "https://orcid.org/0000-0002-4004-2155", "observed_orcids": ["https://orcid.org/0000-0002-4004-2155"]}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Young-Jun Son", "raw_affiliation_strings": ["Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA"], "raw_orcid": "https://orcid.org/0000-0002-4004-2155", "affiliations": [{"raw_affiliation_string": "Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47904, USA", "institution_ids": ["https://openalex.org/I219193219"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9976000189781189, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9976000189781189, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11121", "display_name": "Public Relations and Crisis Communication", "score": 0.000699999975040555, "subfield": {"id": "https://openalex.org/subfields/3315", "display_name": "Communication"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10747", "display_name": "Disaster Management and Resilience", "score": 0.000699999975040555, "subfield": {"id": "https://openalex.org/subfields/3312", "display_name": "Sociology and Political Science"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.1016/j.eswa.2025.127956", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.eswa.2025.127956", "pdf_url": null, "source": {"id": "https://openalex.org/S13144211", "display_name": "Expert Systems with Applications", "issn_l": "0957-4174", "issn": ["0957-4174", "1873-6793"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-2", "ki-jl-2", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Expert Systems with Applications", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4409152738", "doi": "https://doi.org/10.1038/s41592-025-02636-z", "title": "xTrimoPGLM: unified 100-billion-parameter pretrained transformer for deciphering the language of proteins", "publication_year": 2025, "publication_date": "2025-04-03", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101784459", "display_name": "Bo Chen", "orcid": "https://orcid.org/0000-0002-9629-5493", "observed_orcids": ["https://orcid.org/0000-0002-9629-5493", "https://orcid.org/0000-0003-4269-3063"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Bo Chen", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA. cb21@mails.tsinghua.edu.cn", "Tsinghua University, Beijing, China. cb21@mails.tsinghua.edu.cn"], "raw_orcid": "https://orcid.org/0000-0002-9629-5493", "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA. cb21@mails.tsinghua.edu.cn", "institution_ids": []}, {"raw_affiliation_string": "Tsinghua University, Beijing, China. cb21@mails.tsinghua.edu.cn", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5074700282", "display_name": "Xingyi Cheng", "orcid": "https://orcid.org/0009-0005-4510-8693", "observed_orcids": ["https://orcid.org/0009-0005-4510-8693"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Xingyi Cheng", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA. derrickzy@gmail.com"], "raw_orcid": "https://orcid.org/0009-0005-4510-8693", "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA. derrickzy@gmail.com", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Pan Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pan Li", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5018191388", "display_name": "Yangli\u2010ao Geng", "orcid": "https://orcid.org/0000-0003-0173-4041", "observed_orcids": ["https://orcid.org/0000-0003-0173-4041"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yangli-ao Geng", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA", "Tsinghua University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}, {"raw_affiliation_string": "Tsinghua University, Beijing, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010443535", "display_name": "Jing Gong", "orcid": "https://orcid.org/0000-0002-9347-8008", "observed_orcids": ["https://orcid.org/0000-0002-9347-8008"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jing Gong", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Shen Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shen Li", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5093688255", "display_name": "Zhilei Bei", "orcid": "https://orcid.org/0009-0008-7663-5551", "observed_orcids": ["https://orcid.org/0009-0008-7663-5551"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhilei Bei", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA", "Tsinghua University, Beijing, China"], "raw_orcid": "https://orcid.org/0009-0008-7663-5551", "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}, {"raw_affiliation_string": "Tsinghua University, Beijing, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101323614", "display_name": "Xu Tan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu Tan", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100736483", "display_name": "Boyan Wang", "orcid": "https://orcid.org/0000-0003-0088-2106", "observed_orcids": ["https://orcid.org/0000-0003-0088-2106"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Boyan Wang", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA", "Tsinghua University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}, {"raw_affiliation_string": "Tsinghua University, Beijing, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101553817", "display_name": "Xin Zeng", "orcid": "https://orcid.org/0000-0003-1014-2558", "observed_orcids": ["https://orcid.org/0000-0003-1014-2558"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xin Zeng", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103106788", "display_name": "Chi-Ming Liu", "orcid": "https://orcid.org/0009-0003-3278-2983", "observed_orcids": ["https://orcid.org/0009-0003-3278-2983"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chiming Liu", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA"], "raw_orcid": "https://orcid.org/0009-0003-3278-2983", "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005277155", "display_name": "Aohan Zeng", "orcid": "https://orcid.org/0000-0002-8766-0153", "observed_orcids": ["https://orcid.org/0000-0002-8766-0153"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Aohan Zeng", "raw_affiliation_strings": ["Tsinghua University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tsinghua University, Beijing, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052284218", "display_name": "Yuxiao Dong", "orcid": "https://orcid.org/0000-0002-6092-2002", "observed_orcids": ["https://orcid.org/0000-0002-6092-2002"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuxiao Dong", "raw_affiliation_strings": ["Tsinghua University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tsinghua University, Beijing, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044791875", "display_name": "Jie Tang", "orcid": "https://orcid.org/0000-0003-3487-4593", "observed_orcids": ["https://orcid.org/0000-0003-3487-4593"]}, "institutions": [{"id": "https://openalex.org/I99065089", "display_name": "Tsinghua University", "ror": "https://ror.org/03cve4549", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I99065089"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jie Tang", "raw_affiliation_strings": ["Tsinghua University, Beijing, China. jietang@tsinghua.edu.cn"], "raw_orcid": "https://orcid.org/0000-0003-3487-4593", "affiliations": [{"raw_affiliation_string": "Tsinghua University, Beijing, China. jietang@tsinghua.edu.cn", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030589527", "display_name": "Le Song", "orcid": "https://orcid.org/0000-0002-9655-2787", "observed_orcids": ["https://orcid.org/0000-0002-9655-2787"]}, "institutions": [{"id": "https://openalex.org/I4210113480", "display_name": "Mohamed bin Zayed University of Artificial Intelligence", "ror": "https://ror.org/0258gkt32", "country_code": "AE", "type": "education", "lineage": ["https://openalex.org/I4210113480"]}], "countries": ["AE"], "is_corresponding": true, "raw_author_name": "Le Song", "raw_affiliation_strings": ["BioMap Research, Palo Alto, CA, USA. dasongle@gmail.com", "MBZUAI, Abu Dhabi, United Arab Emirates. dasongle@gmail.com"], "raw_orcid": "https://orcid.org/0000-0002-9655-2787", "affiliations": [{"raw_affiliation_string": "BioMap Research, Palo Alto, CA, USA. dasongle@gmail.com", "institution_ids": []}, {"raw_affiliation_string": "MBZUAI, Abu Dhabi, United Arab Emirates. dasongle@gmail.com", "institution_ids": ["https://openalex.org/I4210113480"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.8345000147819519, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.8345000147819519, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10044", "display_name": "Protein Structure and Dynamics", "score": 0.1492999941110611, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T12576", "display_name": "vaccines and immunoinformatics approaches", "score": 0.0012000000569969416, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "doi:10.1038/s41592-025-02636-z", "is_oa": false, "landing_page_url": "https://doi.org/10.1038/s41592-025-02636-z", "pdf_url": null, "source": {"id": "https://openalex.org/S127827428", "display_name": "Nature Methods", "issn_l": "1548-7091", "issn": ["1548-7091", "1548-7105"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-3", "ki-jl-3", "medline", "norway-2"], "host_organization": "https://openalex.org/P4310319908", "host_organization_name": "Nature Portfolio", "host_organization_lineage": ["https://openalex.org/P4310319908", "https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Nature Portfolio", "Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Nature Methods", "raw_type": "journal-article"}, "cited_by_count": 56, "is_retracted": false}, {"id": "https://openalex.org/W4413025787", "doi": "https://doi.org/10.1021/acs.jcim.5c01401", "title": "De Novo Design of Multiple Microplastic-Binding Peptides with a Protein Language Model-Guided Generative Adversarial Network", "publication_year": 2025, "publication_date": "2025-08-06", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100440544", "display_name": "Siyuan Wang", "orcid": "https://orcid.org/0000-0001-9201-2452", "observed_orcids": ["https://orcid.org/0000-0001-9201-2452"]}, "institutions": [{"id": "https://openalex.org/I205783295", "display_name": "Cornell University", "ror": "https://ror.org/05bnh6r87", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I205783295"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Siyuan Wang", "raw_affiliation_strings": ["College of Engineering", "Cornell University"], "raw_orcid": "https://orcid.org/0000-0001-9201-2452", "affiliations": [{"raw_affiliation_string": "College of Engineering", "institution_ids": []}, {"raw_affiliation_string": "Cornell University", "institution_ids": ["https://openalex.org/I205783295"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5057155291", "display_name": "Michael T. Bergman", "orcid": "https://orcid.org/0000-0002-3716-5920", "observed_orcids": ["https://orcid.org/0000-0002-3716-5920"]}, "institutions": [{"id": "https://openalex.org/I137902535", "display_name": "North Carolina State University", "ror": "https://ror.org/04tj63d06", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I137902535"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Michael T. Bergman", "raw_affiliation_strings": ["Department of Chemical and Biomolecular Engineering", "North Carolina State University"], "raw_orcid": "https://orcid.org/0000-0002-3716-5920", "affiliations": [{"raw_affiliation_string": "Department of Chemical and Biomolecular Engineering", "institution_ids": []}, {"raw_affiliation_string": "North Carolina State University", "institution_ids": ["https://openalex.org/I137902535"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5057051008", "display_name": "Carol K. Hall", "orcid": "https://orcid.org/0000-0002-7425-587X", "observed_orcids": ["https://orcid.org/0000-0002-7425-587X"]}, "institutions": [{"id": "https://openalex.org/I137902535", "display_name": "North Carolina State University", "ror": "https://ror.org/04tj63d06", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I137902535"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Carol K. Hall", "raw_affiliation_strings": ["Department of Chemical and Biomolecular Engineering", "North Carolina State University"], "raw_orcid": "https://orcid.org/0000-0002-7425-587X", "affiliations": [{"raw_affiliation_string": "Department of Chemical and Biomolecular Engineering", "institution_ids": []}, {"raw_affiliation_string": "North Carolina State University", "institution_ids": ["https://openalex.org/I137902535"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5062751420", "display_name": "Fengqi You", "orcid": "https://orcid.org/0000-0001-9609-4299", "observed_orcids": ["https://orcid.org/0000-0001-9609-4299"]}, "institutions": [{"id": "https://openalex.org/I205783295", "display_name": "Cornell University", "ror": "https://ror.org/05bnh6r87", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I205783295"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Fengqi You", "raw_affiliation_strings": ["College of Engineering", "Cornell University", "Cornell University AI for Science Institute", "Robert Frederick Smith School of Chemical and Biomolecular Engineering"], "raw_orcid": "https://orcid.org/0000-0001-9609-4299", "affiliations": [{"raw_affiliation_string": "College of Engineering", "institution_ids": []}, {"raw_affiliation_string": "Cornell University", "institution_ids": ["https://openalex.org/I205783295"]}, {"raw_affiliation_string": "Cornell University AI for Science Institute", "institution_ids": ["https://openalex.org/I205783295"]}, {"raw_affiliation_string": "Robert Frederick Smith School of Chemical and Biomolecular Engineering", "institution_ids": []}]}], "abstract_inverted_index": {"Microplastics": [0], "are": [1, 16, 57, 206], "heterogeneous": [2], "pollutants": [3], "that": [4, 50, 109, 128, 188, 205, 224], "pose": [5], "significant": [6], "risks": [7], "to": [8, 47, 52, 102, 130, 150, 158, 162, 172, 201], "ecosystems": [9], "and": [10, 155, 181, 235, 250], "human": [11], "health.": [12], "Innovative": [13], "mitigation": [14], "strategies": [15], "urgently": [17], "needed.": [18], "Plastic-binding": [19], "peptides": [20, 49, 60, 77, 174, 191, 213], "represent": [21], "a": [22, 66, 79, 88, 114, 137, 146], "promising": [23], "eco-friendly": [24], "approach": [25], "for": [26, 70, 82, 136, 178, 232, 246], "detecting": [27], "or": [28], "capturing": [29], "microplastic": [30, 34, 248], "pollution.": [31], "Since": [32], "real-world": [33], "pollution": [35, 249], "consists": [36], "of": [37, 40, 75, 99, 124, 133, 166, 212, 242], "multiple": [38, 53, 83], "types": [39], "plastic,": [41], "it": [42], "would": [43], "be": [44], "particularly": [45], "useful": [46], "have": [48], "bind": [51], "plastics.": [54, 84, 167], "However,": [55], "there": [56], "no": [58], "known": [59], "with": [61, 78, 113, 175], "this": [62, 170], "property.": [63], "We": [64, 168], "present": [65], "generalizable": [67], "AI-driven": [68, 243], "framework": [69, 86, 171], "the": [71, 106, 156, 189, 202, 240], "de": [72], "novo": [73], "design": [74, 112, 173, 245], "plastic-binding": [76], "high": [80, 176, 230], "affinity": [81, 135, 161, 177, 231], "The": [85, 119, 140], "integrates": [87], "pretrained": [89], "protein": [90], "language": [91], "model": [92, 142], "(PLM),": [93], "fine-tuned": [94], "on": [95], "biophysical": [96, 217], "modeling": [97], "data": [98], "peptide": [100, 111, 125, 134, 160, 226, 244, 254], "adsorption": [101, 198], "plastics": [103, 204], "generated": [104, 190], "by": [105], "PepBD": [107], "algorithm,": [108], "guides": [110], "generative": [115], "adversarial": [116], "network": [117], "(GAN).": [118], "PLM": [120], "provides": [121], "appropriate": [122], "embeddings": [123], "physicochemical": [126], "features": [127], "lead": [129], "accurate": [131], "predictions": [132], "given": [138], "plastic.": [139], "GAN": [141], "is": [143], "trained": [144], "via": [145], "modular": [147], "split-training": [148], "strategy": [149], "ensure": [151], "stability,": [152], "sequence": [153], "diversity,": [154], "ability": [157], "optimize": [159], "any": [163], "desired": [164], "combination": [165], "use": [169], "polyethylene,": [179], "polypropylene,": [180], "poly(ethylene": [182], "terephthalate).": [183], "Molecular": [184], "dynamics": [185, 221], "simulations": [186, 222], "confirm": [187], "exhibit": [192], "strong": [193], "multiplastic": [194], "binding,": [195], "having": [196], "average": [197], "free": [199], "energies": [200], "three": [203], "\u223c30%": [207], "more": [208], "favorable": [209], "than": [210], "those": [211], "previously": [214], "designed": [215], "using": [216], "methods.": [218], "Steered": [219], "molecular": [220], "reveal": [223], "one": [225], "has": [227], "an": [228], "exceptionally": [229], "both": [233], "polyethylene": [234], "polypropylene.": [236], "These": [237], "findings": [238], "highlight": [239], "potential": [241], "addressing": [247], "broader": [251], "applications": [252], "in": [253], "engineering.": [255]}, "primary_topic": {"id": "https://openalex.org/T10753", "display_name": "Microplastics and Plastic Pollution", "score": 0.6571999788284302, "subfield": {"id": "https://openalex.org/subfields/2310", "display_name": "Pollution"}, "field": {"id": "https://openalex.org/fields/23", "display_name": "Environmental Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10753", "display_name": "Microplastics and Plastic Pollution", "score": 0.6571999788284302, "subfield": {"id": "https://openalex.org/subfields/2310", "display_name": "Pollution"}, "field": {"id": "https://openalex.org/fields/23", "display_name": "Environmental Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10911", "display_name": "Chemical Synthesis and Analysis", "score": 0.11980000138282776, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10211", "display_name": "Computational Drug Discovery Methods", "score": 0.05700000002980232, "subfield": {"id": "https://openalex.org/subfields/1703", "display_name": "Computational Theory and Mathematics"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1021/acs.jcim.5c01401", "is_oa": false, "landing_page_url": "https://doi.org/10.1021/acs.jcim.5c01401", "pdf_url": null, "source": {"id": "https://openalex.org/S167262187", "display_name": "Journal of Chemical Information and Modeling", "issn_l": "1549-9596", "issn": ["1549-9596", "1549-960X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1", "ki-jl-1", "medline", "norway-2"], "host_organization": "https://openalex.org/P4310320006", "host_organization_name": "American Chemical Society", "host_organization_lineage": ["https://openalex.org/P4310320006"], "host_organization_lineage_names": ["American Chemical Society"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Chemical Information and Modeling", "raw_type": "journal-article"}, "cited_by_count": 13, "is_retracted": false}, {"id": "https://openalex.org/W4415082828", "doi": "https://doi.org/10.48550/arxiv.2503.00634", "title": "Efficiently Editing Mixture-of-Experts Models with Compressed Experts", "publication_year": 2025, "publication_date": "2025-03-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101137979", "display_name": "Yifei He", "orcid": "https://orcid.org/0000-0003-0713-6376", "observed_orcids": ["https://orcid.org/0000-0003-0713-6376"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "He, Yifei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100657670", "display_name": "Yang Liu", "orcid": "https://orcid.org/0000-0002-1297-676X", "observed_orcids": ["https://orcid.org/0000-0002-1297-676X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5035634586", "display_name": "Liang Chen", "orcid": "https://orcid.org/0000-0002-5570-5820", "observed_orcids": ["https://orcid.org/0000-0002-5570-5820"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liang, Chen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030937723", "display_name": "Hany Hassan Awadalla", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Awadalla, Hany Hassan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Mixture-of-Experts": [0], "(MoE)": [1], "models": [2, 12, 67, 148, 187, 196], "have": [3], "become": [4], "a": [5, 17, 32], "key": [6], "approach": [7, 117, 181], "for": [8, 68], "scaling": [9, 193], "large": [10], "language": [11], "efficiently": [13], "by": [14], "activating": [15], "only": [16], "subset": [18], "of": [19, 28, 74, 89, 103, 113, 134, 160, 185], "experts": [20, 30, 35, 41, 51, 80, 91, 122, 128, 156], "during": [21], "training": [22], "and": [23, 76, 151, 174, 191], "inference.": [24], "Typically,": [25], "the": [26, 87, 101, 119], "number": [27, 88], "activated": [29, 50, 90, 127], "presents": [31], "trade-off:": [33], "fewer": [34], "reduce": [36, 86], "computational": [37], "costs,": [38], "while": [39, 92, 123, 141, 167], "more": [40, 169], "improve": [42], "performance.": [43, 95, 144], "Recent": [44], "studies": [45], "reveal": [46], "that": [47, 108, 154], "not": [48], "all": [49], "contribute": [52], "equally": [53], "to": [54, 85, 194], "model": [55, 94], "performance,": [56], "with": [57, 129, 197], "some": [58], "providing": [59], "minimal": [60], "utility,": [61], "particularly": [62], "when": [63], "finetuning": [64], "pretrained": [65], "MoE": [66, 186], "specialized": [69], "downstream": [70], "tasks.": [71], "The": [72, 132], "co-existence": [73], "significant": [75], "redundant": [77], "parameters": [78, 136, 173], "in": [79, 177, 188], "provides": [81], "us": [82], "an": [83], "opportunity": [84], "maintaining": [93], "In": [96], "this": [97], "work,": [98], "we": [99], "propose": [100], "concept": [102], "compressed": [104, 130, 155], "experts,": [105], "lightweight": [106], "modules": [107], "serve": [109], "as": [110], "compact": [111], "representations": [112], "full": [114, 161], "experts.": [115, 131], "Our": [116, 200], "preserves": [118], "most": [120], "important": [121], "replacing": [124], "other": [125], "auxiliary": [126], "reduction": [133], "active": [135, 172], "significantly": [137], "lowers": [138], "inference": [139, 178], "costs": [140], "achieving": [142], "comparable": [143], "Extensive": [145], "experiments": [146], "on": [147], "including": [149], "Phi-MoE": [150], "OLMoE": [152], "demonstrate": [153], "recover": [157], "over": [158], "90%": [159], "expert": [162], "performance": [163], "across": [164], "various": [165], "tasks": [166], "reducing": [168], "than": [170], "30%": [171], "saving": [175], "20%": [176], "costs.": [179], "This": [180], "enables": [182], "efficient": [183], "deployment": [184], "resource-constrained": [189], "settings": [190], "facilitates": [192], "larger": [195], "manageable": [198], "overhead.": [199], "code": [201], "is": [202], "available": [203], "at": [204], "https://github.com/yifei-he/Compressed-Experts.": [205]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.42719998955726624, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.42719998955726624, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.4196999967098236, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.08910000324249268, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2503.00634", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.00634", "pdf_url": "https://arxiv.org/pdf/2503.00634", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7116947916", "doi": "https://doi.org/10.48550/arxiv.2512.17160", "title": "Can Synthetic Images Serve as Effective and Efficient Class Prototypes?", "publication_year": 2025, "publication_date": "2025-12-19", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Shi, Dianxing", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shi, Dianxing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5110877695", "display_name": "Dingjie Fu", "orcid": "https://orcid.org/0009-0009-1327-8312", "observed_orcids": ["https://orcid.org/0009-0009-1327-8312"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fu, Dingjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121084939", "display_name": "Yuqiao Liu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yuqiao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5121106788", "display_name": "Jun Wang", "orcid": "https://orcid.org/0000-0002-1305-5735", "observed_orcids": ["https://orcid.org/0000-0002-1305-5735"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Jun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Vision-Language": [0], "Models": [1], "(VLMs)": [2], "have": [3], "shown": [4], "strong": [5], "performance": [6, 183], "in": [7, 40, 96, 184], "zero-shot": [8, 185], "image": [9], "classification": [10, 186], "tasks.": [11], "However,": [12], "existing": [13], "methods,": [14], "including": [15], "Contrastive": [16], "Language-Image": [17, 73], "Pre-training": [18, 74], "(CLIP),": [19], "all": [20], "rely": [21], "on": [22], "annotated": [23, 166], "text-to-image": [24], "pairs": [25, 168], "for": [26, 57, 164, 193], "aligning": [27], "visual": [28, 106, 110, 121, 141], "and": [29, 37, 108, 117, 137, 146, 169, 177, 188], "textual": [30], "modalities.": [31], "This": [32], "dependency": [33], "introduces": [34], "substantial": [35], "cost": [36], "accuracy": [38], "requirement": [39], "preparing": [41], "high-quality": [42], "datasets.": [43], "At": [44], "the": [45, 109, 120, 135, 162, 175], "same": [46], "time,": [47], "processing": [48], "data": [49], "from": [50], "two": [51], "modes": [52], "also": [53, 61], "requires": [54, 151], "dual-tower": [55], "encoders": [56], "most": [58], "models,": [59], "which": [60], "hinders": [62], "their": [63], "lightweight.": [64], "To": [65], "address": [66], "these": [67, 101, 124], "limitations,": [68], "we": [69], "introduce": [70], "a": [71, 82, 93, 140, 190], "``Contrastive": [72], "via": [75], "Large-Language-Model-based": [76], "Generation": [77], "(LGCLIP)\"": [78], "framework.": [79], "LGCLIP": [80, 143], "leverages": [81], "Large": [83], "Language": [84], "Model": [85], "(LLM)": [86], "to": [87, 126], "generate": [88], "class-specific": [89], "prompts": [90], "that": [91], "guide": [92], "diffusion": [94], "model": [95], "synthesizing": [97], "reference": [98], "images.": [99], "Afterwards": [100], "generated": [102], "images": [103, 114], "serve": [104], "as": [105, 155], "prototypes,": [107], "features": [111, 122], "of": [112, 123, 179], "real": [113], "are": [115], "extracted": [116], "compared": [118], "with": [119], "prototypes": [125], "achieve": [127], "comparative": [128], "prediction.": [129], "By": [130], "optimizing": [131], "prompt": [132], "generation": [133], "through": [134], "LLM": [136], "employing": [138], "only": [139, 152], "encoder,": [142], "remains": [144], "lightweight": [145], "efficient.": [147], "Crucially,": [148], "our": [149], "framework": [150], "class": [153], "labels": [154], "input": [156], "during": [157], "whole": [158], "experimental": [159], "procedure,": [160], "eliminating": [161], "need": [163], "manually": [165], "image-text": [167], "extra": [170], "pre-processing.": [171], "Experimental": [172], "results": [173], "validate": [174], "feasibility": [176], "efficiency": [178], "LGCLIP,": [180], "demonstrating": [181], "great": [182], "tasks": [187], "establishing": [189], "novel": [191], "paradigm": [192], "classification.": [194]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9775000214576721, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9775000214576721, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.020600000396370888, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0010000000474974513, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.48550/arxiv.2512.17160", "is_oa": true, "landing_page_url": "https://doi.org/10.48550/arxiv.2512.17160", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "Preprint"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417519375", "doi": "https://doi.org/10.36227/techrxiv.176620610.03288677/v1", "title": "A Data-Centric Perspective on the Lifecycle of Large Language Models", "publication_year": 2025, "publication_date": "2025-12-20", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5053687590", "display_name": "Jun Rao", "orcid": "https://orcid.org/0000-0001-5804-1508", "observed_orcids": ["https://orcid.org/0000-0001-5804-1508"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jun Rao", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": "https://orcid.org/0000-0001-5804-1508", "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101599729", "display_name": "Xuebo Liu", "orcid": "https://orcid.org/0000-0001-8524-2006", "observed_orcids": ["https://orcid.org/0000-0001-8524-2006"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xuebo Liu", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111342760", "display_name": "Haotian Yan", "orcid": "https://orcid.org/0009-0009-6946-0359", "observed_orcids": ["https://orcid.org/0009-0009-6946-0359"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Haotian Yan", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Junjie Shen", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Junjie Shen", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Haosi Mo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Haosi Mo", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yanghaopeng Dong", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yanghaopeng Dong", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101916750", "display_name": "Zihao Yan", "orcid": "https://orcid.org/0000-0003-2160-9109", "observed_orcids": ["https://orcid.org/0000-0003-2160-9109"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zihao Yan", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100441368", "display_name": "Ziyi Wang", "orcid": "https://orcid.org/0000-0002-1334-7287", "observed_orcids": ["https://orcid.org/0000-0002-1334-7287"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ziyi Wang", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zepeng Lin", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zepeng Lin", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102202218", "display_name": "Xiaojun Meng", "orcid": "https://orcid.org/0009-0006-4337-9331", "observed_orcids": ["https://orcid.org/0009-0006-4337-9331"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiaojun Meng", "raw_affiliation_strings": ["Huawei Large Model Data Technology Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Large Model Data Technology Lab", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5048944308", "display_name": "Zixiong Yu", "orcid": "https://orcid.org/0009-0008-9728-2484", "observed_orcids": ["https://orcid.org/0009-0008-9728-2484"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zixiong Yu", "raw_affiliation_strings": ["Huawei Large Model Data Technology Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Large Model Data Technology Lab", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044738402", "display_name": "Liqun Deng", "orcid": "https://orcid.org/0009-0006-7242-0794", "observed_orcids": ["https://orcid.org/0009-0006-7242-0794"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Liqun Deng", "raw_affiliation_strings": ["Huawei Large Model Data Technology Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Large Model Data Technology Lab", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5020889570", "display_name": "Jiansheng Wei", "orcid": "https://orcid.org/0000-0001-7809-0577", "observed_orcids": ["https://orcid.org/0000-0001-7809-0577"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiansheng Wei", "raw_affiliation_strings": ["Huawei Large Model Data Technology Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Large Model Data Technology Lab", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100727357", "display_name": "Yunhe Wang", "orcid": "https://orcid.org/0000-0002-0923-1441", "observed_orcids": ["https://orcid.org/0000-0002-0923-1441"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yunhe Wang", "raw_affiliation_strings": ["Huawei Large Model Data Technology Lab. 3 Huawei Noah's Ark Lab"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Large Model Data Technology Lab. 3 Huawei Noah's Ark Lab", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100402911", "display_name": "Min Zhang", "orcid": "https://orcid.org/0000-0002-3895-5510", "observed_orcids": ["https://orcid.org/0000-0002-3895-5510"]}, "institutions": [{"id": "https://openalex.org/I204983213", "display_name": "Harbin Institute of Technology", "ror": "https://ror.org/01yqg2h08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I204983213"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Min Zhang", "raw_affiliation_strings": ["Institute of Computing and Intelligence, Harbin Institute of Technology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Computing and Intelligence, Harbin Institute of Technology", "institution_ids": ["https://openalex.org/I204983213"]}]}], "abstract_inverted_index": {"This": [0], "survey": [1, 121], "reframes": [2], "large": [3], "language": [4], "model": [5], "(LLM)": [6], "development": [7], "through": [8], "a": [9, 144], "purely": [10], "data-centric": [11, 155], "lens,": [12], "arguing": [13], "that": [14, 65, 102], "downstream": [15], "capability": [16, 115], "is": [17], "shaped": [18], "primarily": [19], "by": [20], "the": [21, 35, 105], "quality": [22], "and": [23, 48, 55, 62, 74, 77, 86, 92, 131, 139, 151], "evolution": [24], "of": [25], "training": [26, 89], "data": [27, 37, 69, 82, 96, 137], "rather": [28], "than": [29], "parameter": [30], "count.": [31], "We": [32], "systematically": [33], "map": [34], "LLM": [36], "lifecycle": [38], "across": [39], "three": [40], "interconnected": [41], "dimensions:": [42], "(i)": [43], "Existing": [44], "Datasets:": [45], "cataloging": [46], "general": [47], "domain-specific": [49], "corpora": [50], "used": [51], "in": [52], "pre-training,": [53], "SFT": [54], "RL;": [56], "(ii)": [57], "Creation:": [58], "reviewing": [59], "annotation,": [60], "synthesis": [61], "selection": [63], "techniques": [64], "generate": [66], "or": [67], "filter": [68], "while": [70], "balancing": [71], "fidelity,": [72], "diversity": [73], "task": [75], "relevance;": [76], "(iii)": [78], "Strategy:": [79], "summarizing": [80], "how": [81, 109], "ordering,": [83], "mixing,": [84], "replay": [85], "constraints": [87], "influence": [88], "effectiveness,": [90], "efficiency": [91], "truthfulness.": [93], "By": [94], "treating": [95], "as": [97, 136], "an": [98], "active": [99], "epistemic": [100], "agent": [101], "co-evolves": [103], "with": [104, 123], "model,": [106], "we": [107], "reveal": [108], "iterative": [110], "generate-filter-reuse": [111], "cycles": [112], "can": [113], "expand": [114], "frontiers": [116], "without": [117], "architectural": [118], "redesign.": [119], "The": [120], "concludes": [122], "emerging": [124], "challenges,": [125], "domain": [126], "scarcity,": [127], "crossdomain": [128], "reuse,": [129], "privacy,": [130], "outlines": [132], "future": [133], "directions": [134], "such": [135], "flywheels": [138], "model-aware": [140], "filters,": [141], "offering": [142], "researchers": [143], "concise": [145], "roadmap": [146], "for": [147], "building": [148], "performant,": [149], "trustworthy": [150], "domain-expert": [152], "LLMs": [153], "via": [154], "optimization.": [156]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9458000063896179, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9458000063896179, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.03700000047683716, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.006800000090152025, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.36227/techrxiv.176620610.03288677/v1", "is_oa": true, "landing_page_url": "https://doi.org/10.36227/techrxiv.176620610.03288677/v1", "pdf_url": "https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176620610.03288677/v1", "source": null, "license": "cc-by-nc-sa", "license_id": "https://openalex.org/licenses/cc-by-nc-sa", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415650567", "doi": "https://doi.org/10.3389/fdgth.2025.1618510", "title": "Evaluating the role of ChatGPT in rehabilitation medicine: a narrative review", "publication_year": 2025, "publication_date": "2025-10-29", "type": "review", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Meng Luo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I160354188", "display_name": "Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/01tsmvz08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I160354188"]}, {"id": "https://openalex.org/I4210144860", "display_name": "First Affiliated Hospital of Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/059c9vn90", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210144860"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Meng Luo", "raw_affiliation_strings": ["Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China", "The First Clinical Medical School, Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I4210144860"]}, {"raw_affiliation_string": "The First Clinical Medical School, Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I160354188"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhaoyuan Duan", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I160354188", "display_name": "Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/01tsmvz08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I160354188"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhaoyuan Duan", "raw_affiliation_strings": ["School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I160354188"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003714454", "display_name": "Jing Gao", "orcid": "https://orcid.org/0000-0002-1729-2500", "observed_orcids": ["https://orcid.org/0000-0002-1729-2500"]}, "institutions": [{"id": "https://openalex.org/I4210144860", "display_name": "First Affiliated Hospital of Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/059c9vn90", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210144860"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jing Gao", "raw_affiliation_strings": ["Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I4210144860"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5030676228", "display_name": "Yifu Sun", "orcid": "https://orcid.org/0000-0002-5347-3499", "observed_orcids": ["https://orcid.org/0000-0002-5347-3499"]}, "institutions": [{"id": "https://openalex.org/I160354188", "display_name": "Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/01tsmvz08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I160354188"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yalei Sun", "raw_affiliation_strings": ["School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I160354188"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065618208", "display_name": "Lidian Chen", "orcid": "https://orcid.org/0000-0002-8699-0839", "observed_orcids": ["https://orcid.org/0000-0002-8699-0839"]}, "institutions": [{"id": "https://openalex.org/I160354188", "display_name": "Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/01tsmvz08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I160354188"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Lidian Chen", "raw_affiliation_strings": ["School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Rehabilitation Medicine, Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I160354188"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5042241576", "display_name": "Xiaodong Feng", "orcid": "https://orcid.org/0000-0003-2716-1827", "observed_orcids": ["https://orcid.org/0000-0003-2716-1827"]}, "institutions": [{"id": "https://openalex.org/I4210144860", "display_name": "First Affiliated Hospital of Henan University of Traditional Chinese Medicine", "ror": "https://ror.org/059c9vn90", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210144860"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xiaodong Feng", "raw_affiliation_strings": ["Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Rehabilitation Center, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, China", "institution_ids": ["https://openalex.org/I4210144860"]}]}], "abstract_inverted_index": {"Chat": [0], "Generative": [1], "Pretrained": [2], "Transformer": [3], "(ChatGPT)": [4], "has": [5], "emerged": [6], "as": [7], "a": [8], "sophisticated": [9], "artificial": [10], "intelligence": [11], "(AI)": [12], "language": [13], "model": [14], "in": [15, 26, 37, 51, 77, 124, 131], "healthcare.": [16], "This": [17, 113], "narrative": [18], "review": [19, 114], "examines": [20], "ChatGPT's": [21], "current": [22], "applications": [23], "and": [24, 40, 61, 79, 87, 109, 122, 144], "limitations": [25, 108], "rehabilitation": [27, 101, 132], "medicine": [28], "through": [29], "analysing": [30], "multiple": [31], "studies.": [32], "While": [33], "demonstrating": [34], "promising": [35], "performance": [36, 50], "structured": [38], "tasks": [39], "basic": [41], "medical": [42], "guidance,": [43], "significant": [44], "challenges": [45], "persist.": [46], "These": [47], "include": [48], "inconsistent": [49], "complex": [52], "clinical": [53, 83, 142], "scenarios,": [54], "limited": [55], "regional": [56], "adaptability,": [57], "poor": [58], "reference": [59], "reliability,": [60], "inadequate": [62], "safety": [63, 143], "considerations": [64], "for": [65, 119, 137], "special": [66], "populations.": [67], "Although": [68], "innovative": [69], "approaches": [70], "like": [71], "multi-agent": [72], "systems": [73], "show": [74], "potential": [75], "improvements": [76], "accuracy": [78], "interpretability,": [80], "concerns": [81], "regarding": [82], "responsibility,": [84], "data": [85], "security,": [86], "ethical": [88], "implications": [89], "remain": [90], "crucial.": [91], "As": [92], "ChatGPT": [93], "continues": [94], "to": [95, 116], "evolve,": [96], "its": [97], "optimal": [98], "integration": [99, 139], "into": [100], "practice": [102], "requires": [103], "careful": [104], "consideration": [105], "of": [106, 128], "these": [107], "appropriate": [110], "professional": [111], "oversight.": [112], "aims": [115], "provide": [117], "insights": [118], "healthcare": [120], "professionals": [121], "policymakers": [123], "navigating": [125], "the": [126, 135], "implementation": [127], "AI": [129], "assistance": [130], "medicine,": [133], "emphasizing": [134], "need": [136], "balanced": [138], "while": [140], "maintaining": [141], "effectiveness.": [145]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11396", "display_name": "Artificial Intelligence in Healthcare", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/3605", "display_name": "Health Information Management"}, "field": {"id": "https://openalex.org/fields/36", "display_name": "Health Professions"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.3389/fdgth.2025.1618510", "is_oa": true, "landing_page_url": "https://doi.org/10.3389/fdgth.2025.1618510", "pdf_url": "https://public-pages-files-2025.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1618510/pdf", "source": {"id": "https://openalex.org/S4210170686", "display_name": "Frontiers in Digital Health", "issn_l": "2673-253X", "issn": ["2673-253X"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "norway-1"], "host_organization": "https://openalex.org/P4310320527", "host_organization_name": "Frontiers Media", "host_organization_lineage": ["https://openalex.org/P4310320527"], "host_organization_lineage_names": ["Frontiers Media"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Frontiers in Digital Health", "raw_type": "journal-article"}, "cited_by_count": 5, "is_retracted": false}, {"id": "https://openalex.org/W7104259265", "doi": "https://doi.org/10.48550/arxiv.2511.02996", "title": "SCALE-VLP: Soft-Weighted Contrastive Volumetric Vision-Language Pre-training with Spatial-Knowledge Semantics", "publication_year": 2025, "publication_date": "2025-11-04", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Mahdizadeh, Ailar", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mahdizadeh, Ailar", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Moghadam, Puria Azadi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Moghadam, Puria Azadi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "He, Xiangteng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "He, Xiangteng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Mirabbasi, Shahriar", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mirabbasi, Shahriar", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Nasiopoulos, Panos", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nasiopoulos, Panos", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Sigal, Leonid", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sigal, Leonid", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Vision-language": [0], "models": [1], "(VLMs)": [2], "have": [3], "demonstrated": [4], "strong": [5, 98], "cross-modal": [6], "capabilities,": [7], "yet": [8], "most": [9], "work": [10], "remains": [11], "limited": [12, 95], "to": [13, 71, 83, 118, 128], "2D": [14, 46], "data": [15, 34], "and": [16, 28, 51, 75, 90, 104, 106, 140, 144, 166], "assumes": [17], "binary": [18], "supervision": [19], "(i.e.,": [20], "positive": [21], "vs.": [22], "negative": [23], "pairs),": [24], "overlooking": [25], "the": [26, 119, 123, 164], "continuous": [27], "structured": [29], "dependencies": [30], "present": [31], "in": [32, 151], "volumetric": [33, 42, 68], "such": [35], "as": [36, 44], "CT.": [37], "Existing": [38], "approaches": [39], "often": [40], "treat": [41], "scans": [43], "independent": [45], "slices,": [47], "compromising": [48], "spatial": [49, 69], "coherence": [50], "underutilizing": [52], "rich": [53], "clinical": [54], "semantics.": [55], "We": [56], "propose": [57], "SCALE-VLP,": [58], "a": [59], "soft-weighted": [60], "contrastive": [61], "vision-language": [62], "pre-training": [63], "framework": [64], "that": [65], "integrates": [66], "(i)": [67], "semantics": [70, 79], "preserve": [72], "anatomical": [73], "structure": [74], "(ii)": [76], "domain-aware,": [77], "knowledge-infused": [78], "(e.g.,": [80], "radiological": [81], "ontologies)": [82], "guide": [84], "alignment.": [85], "This": [86], "yields": [87], "structurally": [88], "consistent": [89, 110, 161], "semantically": [91], "grounded": [92], "representations": [93], "under": [94], "supervision,": [96], "demonstrating": [97], "cross-task": [99, 165], "transferability": [100], "(retrieval,": [101], "report": [102, 148], "generation,": [103], "classification),": [105], "cross-domain": [107, 167], "generalizability": [108], "with": [109], "gains": [111], "without": [112], "further": [113], "fine-tuning.": [114], "In": [115], "particular,": [116], "compared": [117], "previous": [120], "state": [121], "of": [122, 170], "art,": [124], "SCALE-VLP": [125], "achieves": [126], "up": [127], "4.3x": [129], "higher": [130], "top-1": [131], "CT-report": [132], "retrieval,": [133], "improves": [134], "abnormality": [135], "classification": [136], "by": [137], "10": [138], "points,": [139], "reaches": [141], "ROUGE-L": [142], "0.44": [143], "BERT-F1": [145], "0.89": [146], "for": [147], "generation.": [149], "Further,": [150], "zero-shot": [152], "evaluation": [153], "on": [154], "an": [155], "out-of-domain": [156], "external": [157], "dataset,": [158], "we": [159], "observe": [160], "gains,": [162], "indicating": [163], "generalization": [168], "ability": [169], "SCALE-VLP.": [171]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10824", "display_name": "Image Retrieval and Classification Techniques", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.02996", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.02996", "pdf_url": "https://arxiv.org/pdf/2511.02996", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415348692", "doi": null, "title": "Differential Attention for Multimodal Crisis Event Analysis", "publication_year": 2025, "publication_date": "2025-07-07", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5117489698", "display_name": "Nusrat Munia", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Munia, Nusrat", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhu, Junfeng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhu, Junfeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049581991", "display_name": "Olfa Nasraoui", "orcid": "https://orcid.org/0000-0003-0999-5385", "observed_orcids": ["https://orcid.org/0000-0003-0999-5385"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nasraoui, Olfa", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101789164", "display_name": "Abdullah-Al-Zubaer Imran", "orcid": "https://orcid.org/0000-0001-5215-339X", "observed_orcids": ["https://orcid.org/0000-0001-5215-339X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Imran, Abdullah-Al-Zubaer", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Social": [0], "networks": [1], "can": [2, 15, 23], "be": [3, 24], "a": [4, 17, 48], "valuable": [5], "source": [6], "of": [7, 19, 68, 165], "information": [8, 34, 128], "during": [9], "crisis": [10, 69], "events.": [11], "In": [12, 51], "particular,": [13], "users": [14], "post": [16], "stream": [18, 41], "multimodal": [20, 104, 151], "data": [21, 40, 46, 70, 159], "that": [22, 137, 162, 193], "critical": [25, 127], "for": [26, 189, 196], "real-time": [27], "humanitarian": [28], "response.": [29, 198], "However,": [30], "effectively": [31, 43], "extracting": [32], "meaningful": [33], "from": [35], "this": [36, 52], "large": [37], "and": [38, 42, 60, 91, 113, 171, 186], "noisy": [39], "integrating": [44], "heterogeneous": [45], "remains": [47, 146], "formidable": [49], "challenge.": [50], "work,": [53], "we": [54, 84, 106], "explore": [55], "vision": [56, 90], "language": [57], "models": [58, 178, 188], "(VLMs)": [59], "advanced": [61], "fusion": [62, 173], "strategies": [63, 174], "to": [64, 79, 121, 183], "enhance": [65, 122], "the": [66, 117, 156, 163], "classification": [67, 142, 180], "in": [71, 149, 179], "three": [72, 190], "different": [73, 191], "tasks.": [74], "We": [75], "incorporate": [76], "LLaVA-generated": [77], "text": [78, 92], "improve": [80], "text-image": [81], "alignment.": [82], "Additionally,": [83], "leverage": [85], "Contrastive": [86], "Language-Image": [87], "Pretraining": [88], "(CLIP)-based": [89], "embeddings,": [93], "which,": [94], "without": [95], "task-specific": [96], "fine-tuning,": [97], "outperform": [98], "traditional": [99], "models.": [100], "To": [101], "further": [102], "refine": [103], "fusion,": [105], "employ": [107], "Guided": [108, 144], "Cross": [109], "Attention": [110, 119, 140], "(Guided": [111], "CA)": [112], "combine": [114], "it": [115], "with": [116], "Differential": [118, 139], "mechanism": [120], "feature": [123], "alignment": [124], "by": [125], "emphasizing": [126], "while": [129, 138], "filtering": [130], "out": [131], "irrelevant": [132], "content.": [133], "Our": [134, 199], "results": [135], "show": [136], "improves": [141], "performance,": [143], "CA": [145], "highly": [147], "effective": [148], "aligning": [150], "features.": [152], "Extensive": [153], "experiments": [154], "on": [155], "CrisisMMD": [157], "benchmark": [158], "set": [160], "demonstrate": [161], "combination": [164], "pretrained": [166], "VLMs,": [167], "enriched": [168], "textual": [169], "descriptions,": [170], "adaptive": [172], "consistently": [175], "outperforms": [176], "state-of-the-art": [177], "accuracy,": [181], "contributing": [182], "more": [184], "reliable": [185], "interpretable": [187], "tasks": [192], "are": [194], "crucial": [195], "disaster": [197], "code": [200], "is": [201], "available": [202], "at": [203], "https://github.com/Munia03/Multimodal_Crisis_Event.": [204]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9984999895095825, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9984999895095825, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11121", "display_name": "Public Relations and Crisis Communication", "score": 0.00039999998989515007, "subfield": {"id": "https://openalex.org/subfields/3315", "display_name": "Communication"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2507.05165", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2507.05165", "pdf_url": "https://arxiv.org/pdf/2507.05165", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416130953", "doi": "https://doi.org/10.48550/arxiv.2505.22251", "title": "Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition", "publication_year": 2025, "publication_date": "2025-05-28", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5088360278", "display_name": "Yuan Tseng", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210117523", "display_name": "Samsung (United Kingdom)", "ror": "https://ror.org/01w6gjq94", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I2250650973", "https://openalex.org/I4210117523"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Tseng, Yuan", "raw_affiliation_strings": ["AI Center Cambridge , Samsung , United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "AI Center Cambridge , Samsung , United Kingdom", "institution_ids": ["https://openalex.org/I4210117523"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089505434", "display_name": "Titouan Parcollet", "orcid": "https://orcid.org/0000-0003-0672-1346", "observed_orcids": ["https://orcid.org/0000-0003-0672-1346"]}, "institutions": [{"id": "https://openalex.org/I4210117523", "display_name": "Samsung (United Kingdom)", "ror": "https://ror.org/01w6gjq94", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I2250650973", "https://openalex.org/I4210117523"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Parcollet, Titouan", "raw_affiliation_strings": ["AI Center Cambridge , Samsung , United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "AI Center Cambridge , Samsung , United Kingdom", "institution_ids": ["https://openalex.org/I4210117523"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5045282611", "display_name": "Rogier van Dalen", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210117523", "display_name": "Samsung (United Kingdom)", "ror": "https://ror.org/01w6gjq94", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I2250650973", "https://openalex.org/I4210117523"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "van Dalen, Rogier", "raw_affiliation_strings": ["AI Center Cambridge , Samsung , United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "AI Center Cambridge , Samsung , United Kingdom", "institution_ids": ["https://openalex.org/I4210117523"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003030422", "display_name": "Shucong Zhang", "orcid": "https://orcid.org/0009-0000-8299-8481", "observed_orcids": ["https://orcid.org/0009-0000-8299-8481"]}, "institutions": [{"id": "https://openalex.org/I4210117523", "display_name": "Samsung (United Kingdom)", "ror": "https://ror.org/01w6gjq94", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I2250650973", "https://openalex.org/I4210117523"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Zhang, Shucong", "raw_affiliation_strings": ["AI Center Cambridge , Samsung , United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "AI Center Cambridge , Samsung , United Kingdom", "institution_ids": ["https://openalex.org/I4210117523"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5087701164", "display_name": "Sourav Bhattacharya", "orcid": "https://orcid.org/0000-0001-9670-5264", "observed_orcids": ["https://orcid.org/0000-0001-9670-5264"]}, "institutions": [{"id": "https://openalex.org/I4210117523", "display_name": "Samsung (United Kingdom)", "ror": "https://ror.org/01w6gjq94", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I2250650973", "https://openalex.org/I4210117523"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Bhattacharya, Sourav", "raw_affiliation_strings": ["AI Center Cambridge , Samsung , United Kingdom"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "AI Center Cambridge , Samsung , United Kingdom", "institution_ids": ["https://openalex.org/I4210117523"]}]}], "abstract_inverted_index": {"Recent": [0], "work": [1, 33], "suggests": [2], "that": [3, 35, 124], "large": [4], "language": [5], "models": [6], "(LLMs)": [7], "can": [8, 127], "improve": [9], "performance": [10], "of": [11, 39, 59, 133, 139], "speech": [12, 92, 142], "tasks": [13], "compared": [14], "to": [15, 82, 116], "existing": [16], "systems.": [17], "To": [18, 66], "support": [19], "their": [20], "claims,": [21], "results": [22], "on": [23, 95], "LibriSpeech": [24, 41], "and": [25, 42], "Common": [26, 43], "Voice": [27, 44], "are": [28, 74, 97], "often": [29], "quoted.": [30], "However,": [31], "this": [32], "finds": [34], "a": [36], "substantial": [37], "amount": [38], "the": [40, 57, 107, 137], "evaluation": [45], "sets": [46], "appear": [47], "in": [48], "public": [49], "LLM": [50, 78, 108, 120, 125], "pretraining": [51], "corpora.": [52], "This": [53], "calls": [54], "into": [55], "question": [56], "reliability": [58], "findings": [60], "drawn": [61], "from": [62], "these": [63], "two": [64], "datasets.": [65], "measure": [67], "contamination": [68, 73], "impact,": [69], "LLMs": [70, 96], "trained": [71], "with/without": [72], "compared.": [75, 98], "A": [76], "contaminated": [77], "is": [79, 109], "more": [80], "likely": [81], "generate": [83], "test": [84], "sentences": [85], "it": [86], "has": [87], "seen": [88, 118], "during": [89, 119], "training.": [90, 121], "Then,": [91], "recognisers": [93], "based": [94], "They": [99], "show": [100, 123], "only": [101], "subtle": [102], "error": [103], "rate": [104], "differences": [105], "if": [106], "contaminated,": [110], "but": [111], "assign": [112], "significantly": [113], "higher": [114], "probabilities": [115], "transcriptions": [117], "Results": [122], "outputs": [126], "be": [128], "biased": [129], "by": [130], "tiny": [131], "amounts": [132], "data": [134], "contamination,": [135], "highlighting": [136], "importance": [138], "evaluating": [140], "LLM-based": [141], "systems": [143], "with": [144], "held-out": [145], "data.": [146]}, "primary_topic": {"id": "https://openalex.org/T10201", "display_name": "Speech Recognition and Synthesis", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10201", "display_name": "Speech Recognition and Synthesis", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10860", "display_name": "Speech and Audio Processing", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1711", "display_name": "Signal Processing"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2505.22251", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.22251", "pdf_url": "https://arxiv.org/pdf/2505.22251", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406549107", "doi": "https://doi.org/10.48550/arxiv.2501.09631", "title": "Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework", "publication_year": 2025, "publication_date": "2025-01-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5090858283", "display_name": "Yushen Lin", "orcid": "https://orcid.org/0000-0002-8311-6601", "observed_orcids": ["https://orcid.org/0000-0002-8311-6601"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Lin, Yushen", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049587970", "display_name": "Ruichen Zhang", "orcid": "https://orcid.org/0000-0002-6859-3645", "observed_orcids": ["https://orcid.org/0000-0002-6859-3645"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Zhang, Ruichen", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5106627909", "display_name": "Wenqi Huang", "orcid": "https://orcid.org/0009-0004-9422-4589", "observed_orcids": ["https://orcid.org/0009-0004-9422-4589"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Huang, Wenqi", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100397862", "display_name": "Kai Wang", "orcid": "https://orcid.org/0000-0003-4124-2025", "observed_orcids": ["https://orcid.org/0000-0003-4124-2025", "https://orcid.org/0000-0002-2941-4579", "https://orcid.org/0000-0002-0242-9738", "https://orcid.org/0009-0009-7354-4598"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Wang, Kaidi", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5002904166", "display_name": "Zhiguo Ding", "orcid": "https://orcid.org/0000-0001-5280-384X", "observed_orcids": ["https://orcid.org/0000-0001-5280-384X"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Ding, Zhiguo", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5036412443", "display_name": "Daniel K. C. So", "orcid": "https://orcid.org/0000-0002-7642-1755", "observed_orcids": ["https://orcid.org/0000-0002-7642-1755"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "So, Daniel K. C.", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5091266202", "display_name": "Dusit Tao Niyato", "orcid": "https://orcid.org/0000-0002-7442-7416", "observed_orcids": ["https://orcid.org/0000-0002-7442-7416"]}, "institutions": [{"id": "https://openalex.org/I28407311", "display_name": "University of Manchester", "ror": "https://ror.org/027m9bs27", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I28407311"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Niyato, Dusit", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering , The University of Manchester , M13 9PL , U", "institution_ids": ["https://openalex.org/I28407311"]}]}], "abstract_inverted_index": {"In": [0], "this": [1], "work,": [2], "we": [3, 71, 126], "develop": [4], "a": [5, 28, 73, 81], "specialized": [6], "dataset": [7, 26, 203], "aimed": [8], "at": [9], "enhancing": [10], "the": [11, 92, 113, 116, 120, 140, 154, 170, 176, 183, 188, 210], "evaluation": [12, 213], "and": [13, 36, 55, 68, 85, 100, 138, 182, 204, 212, 225], "fine-tuning": [14, 78, 180, 205], "of": [15, 31, 95, 115, 179, 190, 214], "large": [16], "language": [17, 50], "models": [18, 51, 106, 118], "(LLMs)": [19], "specifically": [20], "for": [21, 52, 87, 104, 221], "wireless": [22, 191, 199, 222], "communication": [23, 200, 223], "applications.": [24, 226], "The": [25], "includes": [27], "diverse": [29], "set": [30], "multi-hop": [32], "questions,": [33], "including": [34, 131], "true/false": [35], "multiple-choice": [37], "types,": [38], "spanning": [39], "varying": [40], "difficulty": [41], "levels": [42], "from": [43, 135], "easy": [44], "to": [45, 64, 108, 144, 198, 208, 217], "hard.": [46], "By": [47], "utilizing": [48], "advanced": [49], "entity": [53], "extraction": [54], "question": [56], "generation,": [57], "rigorous": [58], "data": [59, 97], "curation": [60], "processes": [61], "are": [62, 150], "employed": [63], "maintain": [65], "high": [66], "quality": [67], "relevance.": [69], "Additionally,": [70], "introduce": [72], "Pointwise": [74], "V-Information": [75], "(PVI)": [76], "based": [77], "method,": [79], "providing": [80], "detailed": [82], "theoretical": [83], "analysis": [84], "justification": [86], "its": [88], "use": [89], "in": [90, 164, 169, 187, 219], "quantifying": [91], "information": [93], "content": [94], "training": [96, 211], "with": [98, 119, 167], "2.24\\%": [99], "1.31\\%": [101], "performance": [102, 162], "boost": [103], "different": [105, 129], "compared": [107], "baselines,": [109], "respectively.": [110], "To": [111], "demonstrate": [112], "effectiveness": [114], "fine-tuned": [117], "proposed": [121, 155], "methodologies": [122], "on": [123], "practical": [124], "tasks,": [125, 130], "also": [127, 174], "consider": [128], "summarizing": [132], "optimization": [133], "problems": [134, 142], "technical": [136], "papers": [137], "solving": [139], "mathematical": [141], "related": [143], "non-orthogonal": [145], "multiple": [146], "access": [147], "(NOMA),": [148], "which": [149], "generated": [151], "by": [152], "using": [153], "multi-agent": [156], "framework.": [157], "Simulation": [158], "results": [159], "show": [160], "significant": [161], "gain": [163], "summarization": [165], "tasks": [166], "20.9\\%": [168], "ROUGE-L": [171], "metrics.": [172], "We": [173], "study": [175], "scaling": [177], "laws": [178], "LLMs": [181, 185, 220], "challenges": [184], "face": [186], "field": [189], "communications,": [192], "offering": [193], "insights": [194], "into": [195], "their": [196], "adaptation": [197], "tasks.": [201], "This": [202], "methodology": [206], "aim": [207], "enhance": [209], "LLMs,": [215], "contributing": [216], "advancements": [218], "research": [224]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9945999979972839, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9945999979972839, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.0026000000070780516, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.000699999975040555, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2501.09631", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2501.09631", "pdf_url": "https://arxiv.org/pdf/2501.09631", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415089464", "doi": "https://doi.org/10.48550/arxiv.2509.12110", "title": "When marine radar target detection meets pretrained large language models", "publication_year": 2025, "publication_date": "2025-09-15", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5031079560", "display_name": "Qiying Hu", "orcid": "https://orcid.org/0000-0002-1313-4003", "observed_orcids": ["https://orcid.org/0000-0002-1313-4003"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hu, Qiying", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101695328", "display_name": "Linping Zhang", "orcid": "https://orcid.org/0000-0003-0114-3081", "observed_orcids": ["https://orcid.org/0000-0003-0114-3081"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Linping", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100737123", "display_name": "Xueqian Wang", "orcid": "https://orcid.org/0000-0002-8632-6073", "observed_orcids": ["https://orcid.org/0000-0002-8632-6073", "https://orcid.org/0000-0003-3542-0593"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Xueqian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5018012012", "display_name": "Gang Li", "orcid": "https://orcid.org/0000-0002-8573-1608", "observed_orcids": ["https://orcid.org/0000-0002-8573-1608"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Gang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100345786", "display_name": "Yu Liu", "orcid": "https://orcid.org/0000-0002-5216-3181", "observed_orcids": ["https://orcid.org/0000-0002-5216-3181"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100363146", "display_name": "Xiao-Ping Steven Zhang", "orcid": "https://orcid.org/0000-0001-5241-0069", "observed_orcids": ["https://orcid.org/0000-0001-5241-0069"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Xiao-Ping", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Deep": [0], "learning": [1, 122], "(DL)": [2], "methods": [3], "are": [4], "widely": [5], "used": [6], "to": [7, 65, 99], "extract": [8], "high-dimensional": [9], "patterns": [10], "from": [11, 32], "the": [12, 72, 79, 96, 112, 117], "sequence": [13, 58], "features": [14], "of": [15, 82], "radar": [16, 57], "echo": [17], "signals.": [18], "However,": [19], "conventional": [20], "DL": [21], "algorithms": [22], "face": [23], "challenges": [24], "such": [25], "as": [26], "redundant": [27], "feature": [28, 46, 80], "segments,": [29, 69], "and": [30, 70], "constraints": [31], "restricted": [33], "model": [34], "sizes.": [35], "To": [36], "address": [37], "these": [38, 86], "issues,": [39], "we": [40, 89], "propose": [41], "a": [42, 61, 91], "framework": [43], "that": [44, 111], "integrates": [45], "preprocessing": [47, 54], "with": [48, 78], "large": [49], "language": [50], "models": [51], "(LLMs).": [52], "Our": [53], "module": [55], "tokenizes": [56], "features,": [59], "applies": [60], "patch": [62], "selection": [63], "algorithm": [64], "filter": [66], "out": [67], "uninformative": [68], "projects": [71], "selected": [73], "patches": [74], "into": [75], "embeddings": [76], "compatible": [77], "space": [81], "pre-trained": [83, 92], "LLMs.": [84], "Leveraging": [85], "refined": [87], "embeddings,": [88], "incorporate": [90], "LLM,": [93], "fine-tuning": [94], "only": [95], "normalization": [97], "layers": [98], "reduce": [100], "training": [101], "burdens": [102], "while": [103], "enhancing": [104], "performance.": [105], "Experiments": [106], "on": [107, 120], "measured": [108], "datasets": [109], "demonstrate": [110], "proposed": [113], "method": [114], "significantly": [115], "outperforms": [116], "state-of-the-art": [118], "baselines": [119], "supervised": [121], "tests.": [123]}, "primary_topic": {"id": "https://openalex.org/T10891", "display_name": "Radar Systems and Signal Processing", "score": 0.9434000253677368, "subfield": {"id": "https://openalex.org/subfields/2202", "display_name": "Aerospace Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10891", "display_name": "Radar Systems and Signal Processing", "score": 0.9434000253677368, "subfield": {"id": "https://openalex.org/subfields/2202", "display_name": "Aerospace Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11038", "display_name": "Advanced SAR Imaging Techniques", "score": 0.052299998700618744, "subfield": {"id": "https://openalex.org/subfields/2202", "display_name": "Aerospace Engineering"}, "field": {"id": "https://openalex.org/fields/22", "display_name": "Engineering"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0006000000284984708, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2509.12110", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2509.12110", "pdf_url": "https://arxiv.org/pdf/2509.12110", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4413047021", "doi": "https://doi.org/10.2196/preprints.76636", "title": "Current Landscape and Future Directions Regarding Generative Large Language Models in Stroke Care: Scoping Review (Preprint)", "publication_year": 2025, "publication_date": "2025-04-28", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "XingCe Zhu", "orcid": "https://orcid.org/0000-0002-9974-0003", "observed_orcids": ["https://orcid.org/0000-0002-9974-0003"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "XingCe Zhu", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-9974-0003", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061392055", "display_name": "Wei Dai", "orcid": "https://orcid.org/0000-0001-5090-8832", "observed_orcids": ["https://orcid.org/0000-0001-5090-8832"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wei Dai", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0001-5090-8832", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5020545746", "display_name": "Richard David Evans", "orcid": "https://orcid.org/0000-0001-6367-0560", "observed_orcids": ["https://orcid.org/0000-0001-6367-0560"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Richard Evans", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0001-6367-0560", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5020460741", "display_name": "Xueyu Geng", "orcid": "https://orcid.org/0009-0009-1524-8539", "observed_orcids": ["https://orcid.org/0009-0009-1524-8539"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xueyu Geng", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0009-1524-8539", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025847007", "display_name": "Aruhan Mu", "orcid": "https://orcid.org/0000-0003-1800-9006", "observed_orcids": ["https://orcid.org/0000-0003-1800-9006"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Aruhan Mu", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0003-1800-9006", "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5046256972", "display_name": "Zhiyong Liu", "orcid": "https://orcid.org/0000-0002-5111-9955", "observed_orcids": ["https://orcid.org/0000-0002-5111-9955"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhiyong Liu", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-5111-9955", "affiliations": []}], "abstract_inverted_index": {"BACKGROUND": [0], "Stroke": [1], "has": [2], "a": [3, 56], "major": [4, 115], "impact": [5], "on": [6], "global": [7], "health,": [8], "causing": [9], "long-term": [10], "disability": [11], "and": [12, 35, 44, 60, 66, 73, 97, 104, 108, 133, 146, 175, 220, 253, 264, 292, 297], "straining": [13], "health": [14], "care": [15, 40, 127], "resources.": [16], "Generative": [17], "large": [18], "language": [19], "models": [20, 187], "(gLLMs)": [21], "have": [22], "emerged": [23], "as": [24], "promising": [25], "tools": [26], "to": [27, 54, 88], "help": [28], "address": [29], "these": [30], "challenges,": [31], "but": [32], "their": [33, 130], "applications": [34, 157], "reported": [36], "performance": [37], "in": [38, 69, 78, 118, 229, 251], "stroke": [39, 79, 126, 230], "require": [41], "comprehensive": [42], "mapping": [43, 129], "synthesis.": [45], "OBJECTIVE": [46], "The": [47, 225], "aim": [48], "of": [49, 75, 138, 158, 207, 227, 261, 287], "this": [50, 83, 247], "scoping": [51, 84], "review": [52, 178], "was": [53], "consolidate": [55], "fragmented": [57], "evidence": [58], "base": [59], "examine": [61], "the": [62, 70, 89, 105, 125, 142, 201, 205, 259], "current": [63], "landscape,": [64], "shortcomings,": [65], "future": [67], "directions": [68], "design,": [71], "reporting,": [72, 279], "evaluation": [74, 281], "gLLM-based": [76, 122, 208], "interventions": [77, 123, 239], "care.": [80], "METHODS": [81], "In": [82, 193], "review,": [85], "which": [86], "adhered": [87], "PRISMA-ScR": [90], "(Preferred": [91], "Reporting": [92], "Items": [93], "for": [94, 100, 121, 149, 295], "Systematic": [95], "Reviews": [96], "Meta-Analyses": [98], "extension": [99], "Scoping": [101], "Reviews)": [102], "guidelines": [103], "Population,": [106], "Concept,": [107], "Context": [109], "(PCC)": [110], "framework,": [111], "we": [112, 267], "searched": [113], "6": [114], "scientific": [116], "databases": [117], "December": [119], "2024": [120], "across": [124], "pathway,": [128], "key": [131, 196], "characteristics": [132], "outcomes.": [134], "RESULTS": [135], "A": [136], "total": [137], "25": [139], "studies": [140, 203], "met": [141], "predefined": [143], "eligibility": [144], "criteria": [145], "were": [147, 198], "included": [148, 160, 202], "analysis.": [150], "Retrospective": [151], "designs": [152], "predominated": [153], "(n=16,": [154], "64%).": [155], "Key": [156], "gLLMs": [159, 228], "clinical": [161, 222, 254], "decision-making": [162], "support": [163, 258], "(n=10,": [164], "40%),": [165], "administrative": [166], "assistance": [167], "(n=9,": [168], "36%),": [169], "direct": [170], "patient": [171], "interaction": [172], "(n=5,": [173], "20%),": [174], "automated": [176], "literature": [177], "(n=1,": [179], "4%).": [180], "Implementations": [181], "mainly": [182], "used": [183], "generative": [184], "pretrained": [185], "transformer": [186], "accessed": [188], "through": [189], "task-prompted": [190], "chat": [191], "interfaces.": [192], "total,": [194], "5": [195], "challenges": [197], "identified": [199], "from": [200], "during": [204], "implementation": [206], "interventions:": [209], "ensuring": [210], "factual": [211], "alignment,": [212], "maintaining": [213], "system": [214], "robustness,": [215], "enhancing": [216], "interpretability,": [217], "optimizing": [218], "efficiency,": [219], "facilitating": [221], "adoption.": [223], "CONCLUSIONS": [224], "application": [226], "care,": [231], "while": [232], "promising,": [233], "remains": [234], "relatively": [235, 243], "new,": [236], "with": [237], "most": [238], "reflecting": [240], "early-stage": [241], "or": [242], "simple": [244], "implementations.": [245], "Against": [246], "backdrop,": [248], "critical": [249], "gaps": [250], "research": [252], "translation": [255], "persist.": [256], "To": [257], "development": [260], "clinically": [262], "impactful": [263], "trustworthy": [265], "applications,": [266], "propose": [268], "an": [269], "actionable": [270], "framework": [271], "that": [272], "prioritizes": [273], "real-world": [274], "evidence,": [275], "mandates": [276], "transparent": [277], "technical": [278], "broadens": [280], "beyond": [282], "output": [283], "accuracy,": [284], "strengthens": [285], "validation": [286], "advanced": [288], "task": [289], "adaptation": [290], "strategies,": [291], "investigates": [293], "mechanisms": [294], "safe": [296], "effective": [298], "human-gLLM": [299], "interaction.": [300]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9976000189781189, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9976000189781189, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11396", "display_name": "Artificial Intelligence in Healthcare", "score": 0.0010999999940395355, "subfield": {"id": "https://openalex.org/subfields/3605", "display_name": "Health Information Management"}, "field": {"id": "https://openalex.org/fields/36", "display_name": "Health Professions"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.00039999998989515007, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.2196/preprints.76636", "is_oa": false, "landing_page_url": "https://doi.org/10.2196/preprints.76636", "pdf_url": null, "source": null, "license": null, "license_id": null, "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411094550", "doi": "https://doi.org/10.11591/ijai.v14.i3.pp2367-2378", "title": "MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model", "publication_year": 2025, "publication_date": "2025-06-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113065034", "display_name": "K. Sahit Reddy", "orcid": "https://orcid.org/0009-0000-2982-7640", "observed_orcids": ["https://orcid.org/0009-0000-2982-7640"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "K. Sahit Reddy", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0009-0000-2982-7640", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5093437512", "display_name": "N. Ragavenderan", "orcid": "https://orcid.org/0009-0001-7370-6173", "observed_orcids": ["https://orcid.org/0009-0001-7370-6173"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "N. Ragavenderan", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0009-0001-7370-6173", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Vasanth K.", "orcid": "https://orcid.org/0009-0004-6467-0158", "observed_orcids": ["https://orcid.org/0009-0004-6467-0158"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "Vasanth K.", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0009-0004-6467-0158", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109662470", "display_name": "Ganesh N. Naik", "orcid": "https://orcid.org/0009-0001-6763-3764", "observed_orcids": ["https://orcid.org/0009-0001-6763-3764"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "Ganesh N. Naik", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0009-0001-6763-3764", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003625312", "display_name": "Vishalakshi Prabhu H", "orcid": "https://orcid.org/0000-0001-7149-0412", "observed_orcids": ["https://orcid.org/0000-0001-7149-0412"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "Vishalakshi Prabhu H", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0000-0001-7149-0412", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5078172976", "display_name": "G. S. Nagaraja", "orcid": "https://orcid.org/0000-0001-5517-7039", "observed_orcids": ["https://orcid.org/0000-0001-5517-7039"]}, "institutions": [{"id": "https://openalex.org/I4389425378", "display_name": "R.V. College of Engineering", "ror": "https://ror.org/041re0e60", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4389425378"]}], "countries": [], "is_corresponding": false, "raw_author_name": "Nagaraja G. S.", "raw_affiliation_strings": ["R.V. College of Engineering"], "raw_orcid": "https://orcid.org/0000-0001-5517-7039", "affiliations": [{"raw_affiliation_string": "R.V. College of Engineering", "institution_ids": ["https://openalex.org/I4389425378"]}]}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 57, 134, 193], "natural": [3], "language": [4, 12], "processing": [5], "(NLP)": [6], "have": [7], "been": [8], "driven": [9], "by": [10, 161], "pretrained": [11, 70, 179], "models": [13, 21, 37, 139, 149, 181], "like": [14, 38], "BERT,": [15], "RoBERTa,": [16], "T5,": [17, 51], "and": [18, 40, 50, 79, 96, 112, 122, 144, 155], "GPT.": [19], "These": [20], "excel": [22], "at": [23], "understanding": [24], "complex": [25], "texts,": [26], "but": [27], "biomedical": [28, 77, 89], "literature,": [29], "with": [30, 81], "its": [31], "domain-specific": [32, 82, 195], "terminology,": [33], "poses": [34], "challenges": [35], "that": [36, 84], "Word2Vec": [39], "bidirectional": [41, 60], "long": [42], "short-term": [43], "memory": [44], "(Bi-LSTM)": [45], "can't": [46], "fully": [47], "address.": [48], "GPT": [49], "despite": [52], "capturing": [53, 194], "context,": [54], "fall": [55], "short": [56], "tasks": [58, 168], "needing": [59], "understanding,": [61], "unlike": [62], "BERT.": [63], "Addressing": [64], "this,": [65], "we": [66], "proposed": [67], "MedicalBERT,": [68], "a": [69, 75], "BERT": [71, 159, 180], "model": [72, 92, 133, 160], "trained": [73], "on": [74, 150, 163], "large": [76], "dataset": [78], "equipped": [80], "vocabulary": [83], "enhances": [85], "the": [86, 119, 129, 153, 157, 167, 175, 187], "comprehension": [87], "of": [88, 131, 152, 177, 189], "terminology.": [90], "MedicalBERT": [91, 146], "is": [93], "further": [94], "optimized": [95], "fine-tuned": [97], "to": [98, 127, 136], "address": [99], "diverse": [100], "tasks,": [101, 185], "including": [102], "named": [103], "entity": [104], "recognition,": [105], "relation": [106], "extraction,": [107], "question": [108], "answering,": [109], "sentence": [110], "similarity,": [111], "document": [113], "classification.": [114], "Performance": [115], "metrics": [116], "such": [117, 140], "as": [118, 141], "F1-score,": [120], "accuracy,": [121], "Pearson": [123], "correlation": [124], "are": [125], "employed": [126], "showcase": [128], "efficiency": [130], "our": [132], "comparison": [135], "other": [137], "BERT-based": [138], "BioBERT,": [142], "SciBERT,": [143], "ClinicalBERT.": [145], "outperforms": [147], "these": [148], "most": [151], "benchmarks,": [154], "surpasses": [156], "general-purpose": [158], "5.67%": [162], "average": [164], "across": [165], "all": [166], "evaluated": [169], "respectively.": [170], "This": [171], "work": [172], "also": [173], "underscores": [174], "potential": [176], "leveraging": [178], "for": [182], "medical": [183], "NLP": [184], "demonstrating": [186], "effectiveness": [188], "transfer": [190], "learning": [191], "techniques": [192], "information.": [196]}, "primary_topic": {"id": "https://openalex.org/T11710", "display_name": "Biomedical Text Mining and Ontologies", "score": 0.6689000129699707, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T11710", "display_name": "Biomedical Text Mining and Ontologies", "score": 0.6689000129699707, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.302700012922287, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.014700000174343586, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.11591/ijai.v14.i3.pp2367-2378", "is_oa": true, "landing_page_url": "https://doi.org/10.11591/ijai.v14.i3.pp2367-2378", "pdf_url": null, "source": {"id": "https://openalex.org/S2764408626", "display_name": "IAES International Journal of Artificial Intelligence", "issn_l": "2089-4872", "issn": ["2089-4872", "2252-8938"], "is_oa": true, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1"], "host_organization": "https://openalex.org/P4310315009", "host_organization_name": "Institute of Advanced Engineering and Science (IAES)", "host_organization_lineage": ["https://openalex.org/P4310315009"], "host_organization_lineage_names": ["Institute of Advanced Engineering and Science (IAES)"], "type": "journal"}, "license": "cc-by-sa", "license_id": "https://openalex.org/licenses/cc-by-sa", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IAES International Journal of Artificial Intelligence (IJ-AI)", "raw_type": "journal-article"}, "cited_by_count": 5, "is_retracted": false}, {"id": "https://openalex.org/W4411523003", "doi": "https://doi.org/10.1145/3728949", "title": "Enhanced Prompting Framework for Code Summarization with Large Language Models", "publication_year": 2025, "publication_date": "2025-06-22", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5114184572", "display_name": "Minying Fang", "orcid": "https://orcid.org/0009-0009-2726-6195", "observed_orcids": ["https://orcid.org/0009-0009-2726-6195"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Minying Fang", "raw_affiliation_strings": ["Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "Qingdao University of Science and Technology, Qingdao, China"], "raw_orcid": "https://orcid.org/0009-0009-2726-6195", "affiliations": [{"raw_affiliation_string": "Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}, {"raw_affiliation_string": "Qingdao University of Science and Technology, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Xing Yuan", "orcid": "https://orcid.org/0009-0007-7137-4922", "observed_orcids": ["https://orcid.org/0009-0007-7137-4922"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xing Yuan", "raw_affiliation_strings": ["Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "Qingdao University of Science and Technology, Qingdao, China"], "raw_orcid": "https://orcid.org/0009-0007-7137-4922", "affiliations": [{"raw_affiliation_string": "Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}, {"raw_affiliation_string": "Qingdao University of Science and Technology, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5033673298", "display_name": "Yuying Li", "orcid": "https://orcid.org/0009-0007-0817-4004", "observed_orcids": ["https://orcid.org/0009-0007-0817-4004", "https://orcid.org/0009-0000-1619-1516"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuying Li", "raw_affiliation_strings": ["Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "Qingdao University of Science and Technology, Qingdao, China"], "raw_orcid": "https://orcid.org/0009-0000-1619-1516", "affiliations": [{"raw_affiliation_string": "Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}, {"raw_affiliation_string": "Qingdao University of Science and Technology, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103325773", "display_name": "Haojie Li", "orcid": "https://orcid.org/0009-0001-0863-9576", "observed_orcids": ["https://orcid.org/0009-0001-0863-9576", "https://orcid.org/0009-0007-0334-3681"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Haojie Li", "raw_affiliation_strings": ["Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "Qingdao University of Science and Technology, Qingdao, China"], "raw_orcid": "https://orcid.org/0009-0001-0863-9576", "affiliations": [{"raw_affiliation_string": "Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}, {"raw_affiliation_string": "Qingdao University of Science and Technology, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5075174750", "display_name": "Chunrong Fang", "orcid": "https://orcid.org/0000-0002-9930-7111", "observed_orcids": ["https://orcid.org/0000-0002-9930-7111"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chunrong Fang", "raw_affiliation_strings": ["Nanjing University, The State Key Laboratory for Novel Software Technology, Nanjing, China", "Nanjing University, Nanjing, China"], "raw_orcid": "https://orcid.org/0000-0002-9930-7111", "affiliations": [{"raw_affiliation_string": "Nanjing University, The State Key Laboratory for Novel Software Technology, Nanjing, China", "institution_ids": ["https://openalex.org/I881766915"]}, {"raw_affiliation_string": "Nanjing University, Nanjing, China", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5032222101", "display_name": "Junwei Du", "orcid": "https://orcid.org/0000-0002-2909-2565", "observed_orcids": ["https://orcid.org/0000-0002-2909-2565"]}, "institutions": [{"id": "https://openalex.org/I143413998", "display_name": "Qingdao University of Science and Technology", "ror": "https://ror.org/041j8js14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143413998"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Junwei Du", "raw_affiliation_strings": ["Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "Qingdao University of Science and Technology, Qingdao, China"], "raw_orcid": "https://orcid.org/0000-0002-2909-2565", "affiliations": [{"raw_affiliation_string": "Qingdao University of Science and Technology, School of Data Science, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}, {"raw_affiliation_string": "Qingdao University of Science and Technology, Qingdao, China", "institution_ids": ["https://openalex.org/I143413998"]}]}], "abstract_inverted_index": {"Code": [0, 151], "summarization": [1], "is": [2], "essential": [3], "for": [4, 26, 87, 118, 150], "enhancing": [5], "the": [6, 75, 90, 95, 116, 123, 136, 139, 168, 177, 193, 200, 225, 274, 284], "efficiency": [7], "of": [8, 71, 94, 125, 138, 172, 179, 199, 243, 267], "software": [9, 18], "development,": [10], "enabling": [11], "developers": [12], "to": [13, 37, 121, 189, 211, 262], "swiftly": [14], "comprehend": [15], "and": [16, 81, 92, 144, 166, 170, 204, 250, 277, 289], "maintain": [17], "projects.": [19], "Recent": [20], "efforts": [21], "utilizing": [22], "large": [23], "language": [24], "models": [25], "generating": [27], "precise": [28], "code": [29, 128, 195], "summaries": [30, 96], "have": [31], "shown": [32], "promising": [33], "performance,": [34], "primarily": [35], "due": [36], "their": [38], "advanced": [39], "generative": [40], "capabilities.": [41, 57], "LLMs": [42, 126, 188], "that": [43, 107, 186, 281], "employ": [44], "continuous": [45], "prompting": [46, 217], "techniques": [47], "can": [48, 84], "explore": [49], "a": [50, 184], "broader": [51], "problem": [52], "space,": [53], "potentially": [54], "unlocking": [55], "greater": [56], "However,": [58], "they": [59], "also": [60, 255], "present": [61], "specific": [62], "challenges,": [63], "particularly": [64], "in": [65, 97, 105, 127, 265], "aligning": [66], "with": [67, 111, 153], "task-specific": [68], "situations\u2014a": [69], "strength": [70], "discrete": [72], "prompts.": [73], "Additionally,": [74, 181], "inherent": [76], "differences": [77], "between": [78], "programming": [79, 99, 201], "languages": [80, 83], "natural": [82], "complicate": [85], "comprehension": [86], "LLMs,": [88], "impacting": [89], "accuracy": [91], "relevance": [93], "complex": [98, 194], "scenarios.": [100], "These": [101], "challenges": [102], "may": [103], "result": [104], "outputs": [106, 178], "do": [108], "not": [109], "align": [110], "actual": [112], "task": [113], "needs,": [114], "underscoring": [115], "necessity": [117], "further": [119], "research": [120], "enhance": [122], "effectiveness": [124], "summarization.": [129], "To": [130], "overcome": [131], "these": [132], "limitations,": [133], "we": [134, 158, 182], "combine": [135], "strengths": [137], "two": [140], "approaches": [141], "described": [142], "above": [143], "introduce": [145], "EP4CS\u2014an": [146], "Enhanced": [147], "Prompting": [148], "framework": [149, 219], "Summarization": [152], "Large": [154], "Language": [155], "Models.": [156], "Firstly,": [157], "design": [159], "Mapper,": [160], "which": [161], "undergoes": [162], "pre-training": [163], "on": [164, 176, 232, 245, 248, 252], "pairs": [165], "facilitates": [167], "optimization": [169], "updating": [171], "prompt": [173], "vectors": [174], "based": [175], "LLMs.": [180], "develop": [183], "Struct-Agent": [185], "enables": [187], "more": [190, 290], "accurately": [191], "interpret": [192], "by": [196], "in-depth": [197], "analysis": [198], "language\u2019s": [202], "syntax": [203], "structure.": [205], "Experimental": [206], "results": [207, 272], "indicate": [208], "that,": [209], "compared": [210], "existing": [212], "baseline": [213, 285], "methods,": [214, 286], "our": [215], "enhanced": [216], "learning": [218], "significantly": [220], "improves": [221], "performance": [222], "while": [223, 254], "maintaining": [224], "same": [226], "parameter": [227], "scale.": [228], "Specifically,": [229], "when": [230], "evaluated": [231], "Java": [233], "using": [234], "StarCoderBase": [235], "1": [236], "B": [237], ",": [238], "EP4CS": [239, 282], "achieved": [240], "score": [241], "improvements": [242], "6.59%": [244], "BLEU,": [246], "7.06%": [247], "METEOR,": [249], "4.43%": [251], "ROUGE-L,": [253], "demonstrating": [256], "strong": [257], "robustness.": [258], "And": [259], "it\u2019s": [260], "closer": [261], "real-world": [263], "scenarios": [264], "terms": [266], "semantic": [268], "metrics": [269], "SentenceBERT.": [270], "The": [271], "from": [273], "human": [275], "evaluation": [276], "case": [278], "studies": [279], "show": [280], "surpasses": [283], "producing": [287], "higher-quality": [288], "relevant": [291], "summaries.": [292]}, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1145/3728949", "is_oa": true, "landing_page_url": "https://doi.org/10.1145/3728949", "pdf_url": "https://dl.acm.org/doi/pdf/10.1145/3728949", "source": {"id": "https://openalex.org/S4404663975", "display_name": "Proceedings of the ACM on software engineering.", "issn_l": "2994-970X", "issn": ["2994-970X"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": ["jufo-1"], "host_organization": "https://openalex.org/P4310319798", "host_organization_name": "Association for Computing Machinery", "host_organization_lineage": ["https://openalex.org/P4310319798"], "host_organization_lineage_names": ["Association for Computing Machinery"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Proceedings of the ACM on Software Engineering", "raw_type": "journal-article"}, "cited_by_count": 6, "is_retracted": false}, {"id": "https://openalex.org/W7115585917", "doi": "https://doi.org/10.48550/arxiv.2512.10968", "title": "Benchmarking Automatic Speech Recognition Models for African Languages", "publication_year": 2025, "publication_date": "2025-11-30", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Nahabwe, Alvin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nahabwe, Alvin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Kagumire, Sulaiman", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kagumire, Sulaiman", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Musinguzi, Denis", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Musinguzi, Denis", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Beijuka, Bruno", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Beijuka, Bruno", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Kyagaba, Jonah Mubuuke", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kyagaba, Jonah Mubuuke", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Nabende, Peter", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nabende, Peter", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Katumba, Andrew", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Katumba, Andrew", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Nakatumba-Nabende, Joyce", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nakatumba-Nabende, Joyce", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Automatic": [0], "speech": [1], "recognition": [2], "(ASR)": [3], "for": [4, 190], "African": [5, 48, 72], "languages": [6], "remains": [7], "constrained": [8], "by": [9], "limited": [10], "labeled": [11], "data": [12, 22, 82, 113, 125], "and": [13, 24, 35, 58, 109, 128, 145, 161, 175, 182], "the": [14, 157, 166, 185], "lack": [15], "of": [16, 80, 187], "systematic": [17, 59], "guidance": [18], "on": [19, 76, 156], "model": [20, 141, 171], "selection,": [21], "scaling,": [23], "decoding": [25, 142], "strategies.": [26], "Large": [27], "pre-trained": [28], "systems": [29, 189], "such": [30], "as": [31, 123], "Whisper,": [32], "XLS-R,": [33], "MMS,": [34], "W2v-BERT": [36, 110], "have": [37], "expanded": [38], "access": [39], "to": [40, 86], "ASR": [41, 68, 188], "technology,": [42], "but": [43], "their": [44], "comparative": [45], "behavior": [46], "in": [47, 55, 115, 132], "low-resource": [49, 117], "contexts": [50], "has": [51], "not": [52], "been": [53], "studied": [54], "a": [56], "unified": [57], "way.": [60], "In": [61], "this": [62, 178], "work,": [63], "we": [64, 93], "benchmark": [65], "four": [66], "state-of-the-art": [67], "models": [69, 99], "across": [70], "13": [71], "languages,": [73], "fine-tuning": [74], "them": [75], "progressively": [77], "larger": [78], "subsets": [79], "transcribed": [81], "ranging": [83], "from": [84], "1": [85], "400": [87], "hours.": [88], "Beyond": [89], "reporting": [90], "error": [91], "rates,": [92], "provide": [94], "new": [95], "insights": [96, 183], "into": [97, 184], "why": [98], "behave": [100], "differently": [101], "under": [102], "varying": [103], "conditions.": [104, 134], "We": [105, 135], "show": [106], "that": [107], "MMS": [108], "are": [111], "more": [112, 121], "efficient": [114], "very": [116], "regimes,": [118], "XLS-R": [119], "scales": [120], "effectively": [122], "additional": [124, 153], "becomes": [126], "available,": [127], "Whisper": [129], "demonstrates": [130], "advantages": [131], "mid-resource": [133], "also": [136], "analyze": [137], "where": [138, 148], "external": [139], "language": [140], "yields": [143], "improvements": [144], "identify": [146], "cases": [147], "it": [149], "plateaus": [150], "or": [151], "introduces": [152], "errors,": [154], "depending": [155], "alignment": [158], "between": [159, 168], "acoustic": [160], "text": [162], "resources.": [163], "By": [164], "highlighting": [165], "interaction": [167], "pre-training": [169], "coverage,": [170], "architecture,": [172], "dataset": [173], "domain,": [174], "resource": [176], "availability,": [177], "study": [179], "offers": [180], "practical": [181], "design": [186], "underrepresented": [191], "languages.": [192]}, "primary_topic": {"id": "https://openalex.org/T10201", "display_name": "Speech Recognition and Synthesis", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10201", "display_name": "Speech Recognition and Synthesis", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10860", "display_name": "Speech and Audio Processing", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1711", "display_name": "Signal Processing"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2512.10968", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.10968", "pdf_url": "https://arxiv.org/pdf/2512.10968", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4414580514", "doi": "https://doi.org/10.48550/arxiv.2505.05130", "title": "CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models", "publication_year": 2025, "publication_date": "2025-05-08", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113152753", "display_name": "Mengjun Yi", "orcid": "https://orcid.org/0009-0002-5489-4866", "observed_orcids": ["https://orcid.org/0009-0002-5489-4866"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yi, Mengjun", "raw_affiliation_strings": ["School of Artificial Intelligence , Nanjing University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence , Nanjing University , China", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100332182", "display_name": "Hanwen Zhang", "orcid": "https://orcid.org/0000-0003-0766-1816", "observed_orcids": ["https://orcid.org/0000-0003-0766-1816"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhang, Hanwen", "raw_affiliation_strings": ["School of Artificial Intelligence , Nanjing University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence , Nanjing University , China", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Dou, Hui", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Dou, Hui", "raw_affiliation_strings": ["Department of Computer Science and Technology , Nanjing University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Technology , Nanjing University , China", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000286903", "display_name": "Jian Ming Zhao", "orcid": "https://orcid.org/0000-0003-3265-6461", "observed_orcids": ["https://orcid.org/0000-0003-3265-6461"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhao, Jian", "raw_affiliation_strings": ["School of Electronic Science and Engineering , Nanjing University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electronic Science and Engineering , Nanjing University , China", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5113689725", "display_name": "Furao Shen", "orcid": "https://orcid.org/0000-0003-4308-9247", "observed_orcids": ["https://orcid.org/0000-0003-4308-9247"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shen, Furao", "raw_affiliation_strings": ["School of Artificial Intelligence , Nanjing University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence , Nanjing University , China", "institution_ids": ["https://openalex.org/I881766915"]}]}], "abstract_inverted_index": {"Large": [0], "pre-trained": [1, 75, 135], "Vision-Language": [2], "Models": [3], "(VLMs),": [4], "such": [5], "as": [6], "Contrastive": [7], "Language-Image": [8], "Pre-training": [9], "(CLIP),": [10], "have": [11], "exhibited": [12], "remarkable": [13], "zero-shot": [14], "performance": [15, 176], "across": [16, 58, 89], "various": [17], "image": [18], "classification": [19, 175, 225], "tasks.": [20], "Fine-tuning": [21], "these": [22, 101], "models": [23, 76], "on": [24, 164, 210], "domain-specific": [25], "datasets": [26, 215], "further": [27], "enhances": [28], "their": [29], "effectiveness": [30], "for": [31, 153], "downstream": [32], "applications.": [33], "However,": [34], "fine-tuning": [35, 116], "in": [36, 222], "cloud": [37], "environments": [38], "raises": [39], "significant": [40], "concerns": [41], "regarding": [42], "data": [43, 88, 203], "security": [44], "and": [45, 69, 84, 97, 155, 167, 190, 205, 212, 229], "privacy.": [46], "Federated": [47], "Learning": [48], "(FL)": [49], "offers": [50], "a": [51, 106, 128, 133, 183], "decentralized": [52], "solution": [53], "by": [54, 132], "enabling": [55], "model": [56, 95, 115, 120, 124, 146], "training": [57, 78, 189], "local": [59, 90, 151], "clients": [60, 91, 152], "without": [61], "centralizing": [62], "sensitive": [63], "data,": [64], "but": [65], "the": [66, 139, 156, 165, 170, 174, 188, 193], "high": [67], "communication": [68, 191], "computation": [70], "costs": [71], "of": [72, 141, 177, 224], "transmitting": [73], "full": [74, 114], "during": [77], "limit": [79], "its": [80], "scalability.": [81], "Additionally,": [82], "non-Independent": [83], "Identically": [85], "Distributed": [86], "(non-IID)": [87], "can": [92], "negatively": [93], "impact": [94, 140], "convergence": [96], "performance.": [98], "To": [99], "address": [100], "challenges,": [102], "we": [103], "propose": [104], "CacheFL,": [105], "novel": [107], "federated": [108], "learning": [109], "method": [110], "that": [111, 217], "replaces": [112], "traditional": [113, 220], "with": [117], "lightweight": [118], "cache": [119, 123, 145, 172, 194], "fine-tuning.": [121], "The": [122], "is": [125, 147, 179], "initialized": [126], "using": [127], "class-balanced": [129], "dataset": [130], "generated": [131], "generative": [134], "model,": [136, 173, 195], "effectively": [137], "mitigating": [138], "non-IID": [142], "data.": [143], "This": [144], "then": [148], "distributed": [149], "to": [150, 192], "fine-tuning,": [154], "updated": [157, 171], "parameters": [158], "from": [159], "each": [160], "client": [161], "are": [162], "aggregated": [163], "server": [166], "redistributed.": [168], "With": [169], "CLIP": [178], "improved": [180], "after": [181], "just": [182], "few": [184], "epochs.": [185], "By": [186], "limiting": [187], "CacheFL": [196, 218], "significantly": [197], "reduces": [198], "resource": [199, 227], "demands": [200], "while": [201], "ensuring": [202], "privacy": [204, 230], "security.": [206], "Extensive": [207], "experiments": [208], "conducted": [209], "ImageNet": [211], "10": [213], "additional": [214], "demonstrate": [216], "outperforms": [219], "approaches": [221], "terms": [223], "accuracy,": [226], "efficiency,": [228], "preservation.": [231]}, "primary_topic": {"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.0005000000237487257, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2505.05130", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.05130", "pdf_url": "https://arxiv.org/pdf/2505.05130", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416843288", "doi": "https://doi.org/10.64751/ijpams.2025.v5.n4.pp101-108", "title": "Deep Learning\u2013Based Monitoring of Self-Harm Indicators Across Online Social Communities", "publication_year": 2025, "publication_date": "2025-11-29", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Mr. R.RAVI", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mr. R.RAVI", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120529271", "display_name": "K.NIKHITHA", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "K.NIKHITHA", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100614145", "display_name": "Pooja Pooja", "orcid": "https://orcid.org/0000-0003-2174-7587", "observed_orcids": ["https://orcid.org/0000-0003-2174-7587"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "POOJA", "raw_affiliation_strings": [","], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": ",", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "D.MANMITH REDDY", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "D.MANMITH REDDY", "raw_affiliation_strings": ["Students, Department of Computer Science & Engineering (Data Science) , Malla Reddy College of Engineering , Hyderabad , India"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Students, Department of Computer Science & Engineering (Data Science) , Malla Reddy College of Engineering , Hyderabad , India", "institution_ids": []}]}, {"author_position": "last", "author": {"id": null, "display_name": "S.PRAVEEN", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "S.PRAVEEN", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Self-harm": [0], "is": [1, 74], "a": [2, 19, 101], "rising": [3], "global": [4], "public": [5], "health": [6], "concern,": [7], "and": [8, 24, 50, 88, 110, 127, 146, 164, 176, 200, 209, 221, 228], "early": [9], "detection": [10], "of": [11, 67, 81, 156, 169], "psychological": [12, 132], "distress": [13], "within": [14], "online": [15, 115], "communities": [16], "can": [17], "play": [18], "crucial": [20], "role": [21], "in": [22, 33, 143, 197, 224], "prevention": [23], "timely": [25], "intervention": [26], "[1],": [27, 118], "[4].": [28], "With": [29], "the": [30, 78, 174, 191, 213], "rapid": [31, 83], "increase": [32], "social": [34, 72, 116, 161, 186], "media": [35, 187], "usage,": [36], "individuals": [37], "experiencing": [38], "emotional": [39, 139], "instability": [40], "often": [41], "express": [42], "their": [43], "feelings": [44], "through": [45], "text": [46, 159], "posts,": [47], "comments,": [48], "hashtags,": [49], "multimedia": [51], "interactions,": [52], "creating": [53], "digital": [54], "footprints": [55], "that": [56, 190], "may": [57], "reflect": [58], "underlying": [59], "self-harm": [60, 112, 171, 234], "ideation": [61], "[2],": [62, 179], "[8].": [63], "However,": [64], "manual": [65], "monitoring": [66, 104], "self-harm\u2013related": [68], "discourse": [69], "across": [70, 114], "large-scale": [71, 210], "networks": [73], "impractical": [75], "due": [76], "to": [77, 107, 130, 232], "vast": [79], "volume": [80], "data,": [82], "information": [84], "diffusion,": [85], "linguistic": [86], "ambiguity,": [87], "privacy-preserving": [89], "user": [90], "anonymity": [91], "[17],": [92], "[19].": [93], "To": [94], "address": [95], "these": [96], "challenges,": [97], "this": [98], "research": [99], "introduces": [100], "deep": [102], "learning\u2013based": [103], "framework": [105, 192], "designed": [106], "automatically": [108], "detect": [109], "track": [111], "indicators": [113], "platforms": [117], "[5].": [119], "The": [120, 154], "proposed": [121, 214], "system": [122], "utilizes": [123], "pretrained": [124], "language": [125], "models": [126], "transformer-driven": [128], "architectures": [129], "extract": [131], "cues": [133], "from": [134], "user-generated": [135], "content,": [136], "while": [137], "temporal": [138], "modeling": [140], "captures": [141], "variations": [142], "sentiment,": [144, 160], "intent,": [145], "behavioral": [147, 211], "patterns": [148], "over": [149], "time": [150], "[3],": [151], "[6],": [152], "[13].": [153], "integration": [155], "multimodal": [157], "features\u2014including": [158], "engagement": [162], "signals,": [163], "interaction": [165], "patterns\u2014enables": [166], "accurate": [167], "forecasting": [168], "emerging": [170], "trends": [172], "at": [173], "community": [175], "population": [177], "levels": [178], "[9],": [180], "[14].": [181], "Experimental": [182], "results": [183], "on": [184], "real-world": [185], "datasets": [188], "demonstrate": [189], "surpasses": [193], "traditional": [194], "machine-learning": [195], "baselines": [196], "precision,": [198], "recall,": [199], "early-warning": [201], "sensitivity": [202], "[5],": [203], "[7],": [204], "[10].": [205], "By": [206], "offering": [207], "continuous": [208], "surveillance,": [212], "solution": [215], "supports": [216], "mental-health": [217], "organizations,": [218], "policy": [219], "makers,": [220], "crisis-response": [222], "teams": [223], "identifying": [225], "high-risk": [226], "groups": [227], "designing": [229], "proactive": [230], "interventions": [231], "mitigate": [233], "incidents": [235], "[11],": [236], "[15],": [237], "[20].": [238]}, "primary_topic": {"id": "https://openalex.org/T12488", "display_name": "Mental Health via Writing", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/3207", "display_name": "Social Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T12488", "display_name": "Mental Health via Writing", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/3207", "display_name": "Social Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10376", "display_name": "Suicide and Self-Harm Studies", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/3203", "display_name": "Clinical Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T12262", "display_name": "Hate Speech and Cyberbullying Detection", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.64751/ijpams.2025.v5.n4.pp101-108", "is_oa": true, "landing_page_url": "https://doi.org/10.64751/ijpams.2025.v5.n4.pp101-108", "pdf_url": "https://ijpams.com/journal/index.php/ijpams/article/download/102/102", "source": {"id": "https://openalex.org/S5407053032", "display_name": "International Journal of Pharmacy with Medical Sciences", "issn_l": "3068-2738", "issn": ["3068-2738"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Pharmacy with Medical Sciences", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7106679457", "doi": "https://doi.org/10.48550/arxiv.2511.18024", "title": "Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems", "publication_year": 2025, "publication_date": "2025-11-22", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Arviv, Dor", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Arviv, Dor", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Elisha, Yehonatan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Elisha, Yehonatan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Barkan, Oren", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Barkan, Oren", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Koenigstein, Noam", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Koenigstein, Noam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0], "present": [1], "a": [2, 30, 66, 74, 128], "method": [3, 119], "for": [4, 131], "extracting": [5], "\\emph{monosemantic}": [6], "neurons,": [7], "defined": [8], "as": [9, 95], "latent": [10, 81], "dimensions": [11], "that": [12, 71], "align": [13], "with": [14, 83], "coherent": [15], "and": [16, 21, 58, 77, 98, 101, 110, 125, 133, 137], "interpretable": [17, 132], "concepts,": [18], "from": [19], "user": [20, 57], "item": [22, 59], "embeddings": [23], "in": [24, 49], "recommender": [25, 76], "systems.": [26], "Our": [27, 118], "approach": [28], "employs": [29], "Sparse": [31], "Autoencoder": [32], "(SAE)": [33], "to": [34, 43], "reveal": [35], "semantic": [36], "structure": [37, 82], "within": [38], "pretrained": [39], "representations.": [40], "In": [41], "contrast": [42], "work": [44], "on": [45], "language": [46], "models,": [47], "monosemanticity": [48], "recommendation": [50, 123], "must": [51], "preserve": [52], "the": [53, 79, 84, 115], "interactions": [54], "between": [55], "separate": [56], "embeddings.": [60], "To": [61], "achieve": [62], "this,": [63], "we": [64], "introduce": [65], "\\emph{prediction": [67], "aware}": [68], "training": [69], "objective": [70], "backpropagates": [72], "through": [73], "frozen": [75], "aligns": [78], "learned": [80], "model's": [85], "user-item": [86], "affinity": [87], "predictions.": [88], "The": [89], "resulting": [90], "neurons": [91], "capture": [92], "properties": [93], "such": [94], "genre,": [96], "popularity,": [97], "temporal": [99], "trends,": [100], "support": [102], "post": [103], "hoc": [104], "control": [105], "operations": [106], "including": [107], "targeted": [108], "filtering": [109], "content": [111], "promotion": [112], "without": [113], "modifying": [114], "base": [116], "model.": [117], "generalizes": [120], "across": [121], "different": [122], "models": [124], "datasets,": [126], "providing": [127], "practical": [129], "tool": [130], "controllable": [134], "personalization.": [135], "Code": [136], "evaluation": [138], "resources": [139], "are": [140], "available": [141], "at": [142], "https://github.com/DeltaLabTLV/Monosemanticity4Rec.": [143]}, "primary_topic": {"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.0007999999797903001, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.48550/arxiv.2511.18024", "is_oa": true, "landing_page_url": "https://doi.org/10.48550/arxiv.2511.18024", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "Preprint"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4409476402", "doi": "https://doi.org/10.2139/ssrn.5140745", "title": "Navigating Europe's Artificial Intelligence Act: Application of LLMs in Classrooms", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5033870480", "display_name": "Upasana Dasgupta", "orcid": "https://orcid.org/0009-0004-0591-0449", "observed_orcids": ["https://orcid.org/0009-0004-0591-0449"]}, "institutions": [{"id": "https://openalex.org/I4210129200", "display_name": "O. P. Jindal Global University", "ror": "https://ror.org/03j2ta742", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I4210129200"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Upasana Dasgupta", "raw_affiliation_strings": ["O.P. Jindal Global University - Jindal Global Law School"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "O.P. Jindal Global University - Jindal Global Law School", "institution_ids": ["https://openalex.org/I4210129200"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5073597081", "display_name": "Rwitajit Majumdar", "orcid": "https://orcid.org/0000-0003-4671-0238", "observed_orcids": ["https://orcid.org/0000-0003-4671-0238"]}, "institutions": [{"id": "https://openalex.org/I96036126", "display_name": "Kumamoto University", "ror": "https://ror.org/02cgss904", "country_code": "JP", "type": "education", "lineage": ["https://openalex.org/I96036126"]}], "countries": ["JP"], "is_corresponding": true, "raw_author_name": "Rwitajit Majumdar", "raw_affiliation_strings": ["Kumamoto University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Kumamoto University", "institution_ids": ["https://openalex.org/I96036126"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T14414", "display_name": "Artificial Intelligence in Education", "score": 0.6586999893188477, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T14414", "display_name": "Artificial Intelligence in Education", "score": 0.6586999893188477, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13364", "display_name": "Digitalization, Law, and Regulation", "score": 0.15489999949932098, "subfield": {"id": "https://openalex.org/subfields/3308", "display_name": "Law"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T13851", "display_name": "Law, AI, and Intellectual Property", "score": 0.05920000001788139, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.2139/ssrn.5140745", "is_oa": true, "landing_page_url": "https://doi.org/10.2139/ssrn.5140745", "pdf_url": null, "source": {"id": "https://openalex.org/S4210172589", "display_name": "SSRN Electronic Journal", "issn_l": "1556-5068", "issn": ["1556-5068"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I1318003438", "host_organization_name": "RELX Group (Netherlands)", "host_organization_lineage": ["https://openalex.org/I1318003438"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4413345388", "doi": "https://doi.org/10.1103/db1b-hy16", "title": "RAG-ESM: Improving Pretrained Protein Language Models via Sequence Retrieval", "publication_year": 2025, "publication_date": "2025-07-30", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5086331988", "display_name": "Damiano Sgarbossa", "orcid": "https://orcid.org/0000-0002-7878-6061", "observed_orcids": ["https://orcid.org/0000-0002-7878-6061"]}, "institutions": [{"id": "https://openalex.org/I12708293", "display_name": "SIB Swiss Institute of Bioinformatics", "ror": "https://ror.org/002n09z45", "country_code": "CH", "type": "nonprofit", "lineage": ["https://openalex.org/I12708293"]}, {"id": "https://openalex.org/I5124864", "display_name": "\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne", "ror": "https://ror.org/02s376052", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I2799323385", "https://openalex.org/I5124864"]}], "countries": ["CH"], "is_corresponding": true, "raw_author_name": "Damiano Sgarbossa", "raw_affiliation_strings": ["EPFL", "SIB Swiss Institute of Bioinformatics", "Institute of Bioengineering, School of Life Sciences, EPFL, CH-1015 Lausanne, Switzerland and SIB Swiss Institute of Bioinformatics, CH-1015 Lausanne, Switzerland"], "raw_orcid": "https://orcid.org/0000-0002-7878-6061", "affiliations": [{"raw_affiliation_string": "EPFL", "institution_ids": ["https://openalex.org/I5124864"]}, {"raw_affiliation_string": "SIB Swiss Institute of Bioinformatics", "institution_ids": ["https://openalex.org/I12708293"]}, {"raw_affiliation_string": "Institute of Bioengineering, School of Life Sciences, EPFL, CH-1015 Lausanne, Switzerland and SIB Swiss Institute of Bioinformatics, CH-1015 Lausanne, Switzerland", "institution_ids": ["https://openalex.org/I12708293", "https://openalex.org/I5124864"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030010662", "display_name": "Anne\u2010Florence Bitbol", "orcid": "https://orcid.org/0000-0003-1020-494X", "observed_orcids": ["https://orcid.org/0000-0003-1020-494X"]}, "institutions": [{"id": "https://openalex.org/I12708293", "display_name": "SIB Swiss Institute of Bioinformatics", "ror": "https://ror.org/002n09z45", "country_code": "CH", "type": "nonprofit", "lineage": ["https://openalex.org/I12708293"]}, {"id": "https://openalex.org/I5124864", "display_name": "\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne", "ror": "https://ror.org/02s376052", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I2799323385", "https://openalex.org/I5124864"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Anne-Florence Bitbol", "raw_affiliation_strings": ["EPFL", "SIB Swiss Institute of Bioinformatics", "Institute of Bioengineering, School of Life Sciences, EPFL, CH-1015 Lausanne, Switzerland and SIB Swiss Institute of Bioinformatics, CH-1015 Lausanne, Switzerland"], "raw_orcid": "https://orcid.org/0000-0003-1020-494X", "affiliations": [{"raw_affiliation_string": "EPFL", "institution_ids": ["https://openalex.org/I5124864"]}, {"raw_affiliation_string": "SIB Swiss Institute of Bioinformatics", "institution_ids": ["https://openalex.org/I12708293"]}, {"raw_affiliation_string": "Institute of Bioengineering, School of Life Sciences, EPFL, CH-1015 Lausanne, Switzerland and SIB Swiss Institute of Bioinformatics, CH-1015 Lausanne, Switzerland", "institution_ids": ["https://openalex.org/I12708293", "https://openalex.org/I5124864"]}]}], "abstract_inverted_index": {"Protein": [0], "language": [1, 52], "models": [2, 53, 73, 77], "are": [3, 15], "significantly": [4], "advancing": [5], "the": [6], "modeling": [7], "of": [8, 13, 19, 61, 95], "sequence-function": [9], "relationships.": [10], "However,": [11], "most": [12], "them": [14, 34], "not": [16], "directly": [17], "informed": [18], "homology": [20, 35], "and": [21, 65, 105, 121, 136], "evolutionary": [22], "relationships": [23], "between": [24], "protein": [25, 51, 118, 138], "sequences.": [26], "Here,": [27], "we": [28], "propose": [29], "a": [30, 40, 58, 99], "method": [31, 128], "to": [32, 47], "make": [33], "aware.": [36], "We": [37, 69, 83], "introduce": [38], "RAG-ESM,": [39], "retrieval-augmented-generation": [41], "(RAG)": [42], "framework": [43], "that": [44, 71, 85], "allows": [45], "us": [46], "condition": [48], "pretrained": [49], "ESM2": [50, 76], "on": [54, 108], "homologous": [55], "sequences,": [56], "using": [57, 98], "minimal": [59, 66], "number": [60], "additional": [62], "cross-attention": [63, 93], "parameters": [64], "computational": [67], "cost.": [68], "show": [70], "RAG-ESM": [72, 112], "outperform": [74], "larger": [75], "for": [78, 103, 116, 133], "masked": [79], "amino": [80], "acid": [81], "prediction.": [82], "find": [84], "sequence": [86, 119], "alignment": [87], "capabilities": [88], "spontaneously": [89], "emerge": [90], "in": [91], "specific": [92], "heads": [94], "RAG-ESM.": [96], "By": [97], "discrete": [100], "diffusion": [101], "objective": [102], "training,": [104], "by": [106], "conditioning": [107], "homologs": [109], "during": [110], "inference,": [111], "reaches": [113], "state-of-the-art": [114], "performance": [115], "conditional": [117], "generation": [120], "motif": [122], "scaffolding,": [123], "among": [124], "sequence-based": [125], "models.": [126], "Our": [127], "thus": [129], "possesses": [130], "strong": [131], "potential": [132], "scalable,": [134], "efficient": [135], "controlled": [137], "engineering.": [139]}, "primary_topic": {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.9063000082969666, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.9063000082969666, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10044", "display_name": "Protein Structure and Dynamics", "score": 0.0722000002861023, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0026000000070780516, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1103/db1b-hy16", "is_oa": true, "landing_page_url": "https://doi.org/10.1103/db1b-hy16", "pdf_url": "http://link.aps.org/pdf/10.1103/db1b-hy16", "source": {"id": "https://openalex.org/S4387291267", "display_name": "PRX Life", "issn_l": "2835-8279", "issn": ["2835-8279"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj"], "host_organization": "https://openalex.org/P4310320261", "host_organization_name": "American Physical Society", "host_organization_lineage": ["https://openalex.org/P4310320261"], "host_organization_lineage_names": ["American Physical Society"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "PRX Life", "raw_type": "journal-article"}, "cited_by_count": 3, "is_retracted": false}, {"id": "https://openalex.org/W4409082853", "doi": "https://doi.org/10.4108/eetpht.11.9010", "title": "SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection", "publication_year": 2025, "publication_date": "2025-04-02", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5029879679", "display_name": "Dimitrios Kollias", "orcid": "https://orcid.org/0000-0002-8188-3751", "observed_orcids": ["https://orcid.org/0000-0002-8188-3751"]}, "institutions": [{"id": "https://openalex.org/I166337079", "display_name": "Queen Mary University of London", "ror": "https://ror.org/026zzn846", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I124357947", "https://openalex.org/I166337079"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Dimitrios Kollias", "raw_affiliation_strings": ["Queen Mary University of London"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Queen Mary University of London", "institution_ids": ["https://openalex.org/I166337079"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016292531", "display_name": "\u0391\u03bd\u03b1\u03c3\u03c4\u03ac\u03c3\u03b9\u03bf\u03c2 \u0391\u03c1\u03c3\u03ad\u03bd\u03bf\u03c2", "orcid": "https://orcid.org/0009-0000-0332-6194", "observed_orcids": ["https://orcid.org/0009-0000-0332-6194"]}, "institutions": [{"id": "https://openalex.org/I174458059", "display_name": "National Technical University of Athens", "ror": "https://ror.org/03cx6bg69", "country_code": "GR", "type": "education", "lineage": ["https://openalex.org/I174458059"]}], "countries": ["GR"], "is_corresponding": false, "raw_author_name": "Anastasios Arsenos", "raw_affiliation_strings": ["National Technical University of Athens"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Technical University of Athens", "institution_ids": ["https://openalex.org/I174458059"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5081594118", "display_name": "James Wingate", "orcid": "https://orcid.org/0000-0003-1253-0984", "observed_orcids": ["https://orcid.org/0000-0003-1253-0984"]}, "institutions": [{"id": "https://openalex.org/I51532219", "display_name": "University of Lincoln", "ror": "https://ror.org/03yeq9x20", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I51532219"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "James Wingate", "raw_affiliation_strings": ["University of Lincoln"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Lincoln", "institution_ids": ["https://openalex.org/I51532219"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5001457450", "display_name": "Stefanos Kollias", "orcid": "https://orcid.org/0000-0003-2899-0598", "observed_orcids": ["https://orcid.org/0000-0003-2899-0598", "https://orcid.org/0000-0002-2879-9286"]}, "institutions": [{"id": "https://openalex.org/I174458059", "display_name": "National Technical University of Athens", "ror": "https://ror.org/03cx6bg69", "country_code": "GR", "type": "education", "lineage": ["https://openalex.org/I174458059"]}], "countries": ["GR"], "is_corresponding": false, "raw_author_name": "Stefanos Kollias", "raw_affiliation_strings": ["National Technical University of Athens"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National Technical University of Athens", "institution_ids": ["https://openalex.org/I174458059"]}]}], "abstract_inverted_index": {"This": [0], "paper": [1], "presents": [2], "a": [3, 40, 55, 66], "new": [4], "approach": [5, 38], "for": [6, 34, 61, 73, 108, 123, 165, 187], "effective": [7], "segmentation": [8, 74, 121, 163, 188], "of": [9, 27, 42, 79, 110, 142, 189], "images": [10, 29], "that": [11, 22, 45, 75, 136], "can": [12], "be": [13], "integrated": [14], "into": [15, 106], "any": [16], "model": [17], "and": [18, 85, 95, 112, 148, 159], "methodology;": [19], "the": [20, 47, 77, 93, 127, 134, 140, 146, 161, 166, 177, 190], "paradigm": [21], "we": [23], "choose": [24], "is": [25, 71, 153], "classification": [26, 109], "medical": [28], "(3-D": [30], "chest": [31], "CT": [32, 48, 99, 128, 191], "scans)": [33], "Covid-19": [35, 62, 172], "detection.": [36, 63], "Our": [37], "includes": [39], "combination": [41], "vision-language": [43], "models": [44], "segment": [46, 92], "scans,": [49, 100], "which": [50, 175], "are": [51, 137, 168], "then": [52, 130], "fed": [53], "to": [54, 90], "deep": [56], "neural": [57], "architecture,": [58], "named": [59, 69], "RACNet,": [60], "In": [64], "particular,": [65], "novel": [67], "framework,": [68], "SAM2CLIP2SAM,": [70], "introduced": [72], "leverages": [76], "strengths": [78], "both": [80], "Segment": [81], "Anything": [82], "Model": [83], "(SAM)": [84], "Contrastive": [86], "Language-Image": [87], "Pre-Training": [88], "(CLIP)": [89], "accurately": [91], "right": [94, 147], "left": [96, 149], "lungs": [97], "in": [98, 126], "subsequently": [101], "feeding": [102], "these": [103, 155], "segmented": [104], "outputs": [105], "RACNet": [107], "COVID-19": [111], "non-COVID-19": [113], "cases.": [114], "At": [115], "first,": [116], "SAM": [117, 152], "produces": [118], "multiple": [119], "part-based": [120], "masks": [122, 135], "each": [124], "slice": [125], "scan;": [129], "CLIP": [131], "selects": [132], "only": [133], "associated": [138], "with": [139], "regions": [141], "interest": [143], "(ROIs),": [144], "i.e.,": [145], "lungs;": [150], "finally": [151], "given": [154], "ROIs": [156], "as": [157], "prompts": [158], "generates": [160], "final": [162], "mask": [164], "lungs.Experiments": [167], "presented": [169], "across": [170], "two": [171], "annotated": [173], "databases": [174], "illustrate": [176], "improved": [178], "performance": [179], "obtained": [180], "when": [181], "our": [182], "method": [183], "has": [184], "been": [185], "used": [186], "scans.": [192]}, "primary_topic": {"id": "https://openalex.org/T11775", "display_name": "COVID-19 diagnosis using AI", "score": 0.9883000254631042, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11775", "display_name": "COVID-19 diagnosis using AI", "score": 0.9883000254631042, "subfield": {"id": "https://openalex.org/subfields/2741", "display_name": "Radiology, Nuclear Medicine and Imaging"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10052", "display_name": "Medical Image Segmentation Techniques", "score": 0.00930000003427267, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0007999999797903001, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.4108/eetpht.11.9010", "is_oa": true, "landing_page_url": "https://doi.org/10.4108/eetpht.11.9010", "pdf_url": "https://publications.eai.eu/index.php/phat/article/download/9010/3546", "source": {"id": "https://openalex.org/S2736858385", "display_name": "EAI Endorsed Transactions on Pervasive Health and Technology", "issn_l": "2411-7145", "issn": ["2411-7145"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj"], "host_organization": "https://openalex.org/P4310321144", "host_organization_name": "Institute for Computer Sciences, Social Informatics and Telecommunications Engineering", "host_organization_lineage": ["https://openalex.org/P4310321144"], "host_organization_lineage_names": ["Institute for Computer Sciences, Social Informatics and Telecommunications Engineering"], "type": "journal"}, "license": "cc-by-nc-sa", "license_id": "https://openalex.org/licenses/cc-by-nc-sa", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "EAI Endorsed Transactions on Pervasive Health and Technology", "raw_type": "journal-article"}, "cited_by_count": 4, "is_retracted": false}, {"id": "https://openalex.org/W4409721863", "doi": "https://doi.org/10.2196/preprints.76433", "title": "Multi-Criteria Optimization of Language Models for HFpEF Symptom Detection in Spanish Electronic Health Records (Preprint)", "publication_year": 2025, "publication_date": "2025-04-23", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5002165918", "display_name": "Jacinto Mata V\u00e1zquez", "orcid": "https://orcid.org/0000-0001-5329-9622", "observed_orcids": ["https://orcid.org/0000-0001-5329-9622"]}, "institutions": [{"id": "https://openalex.org/I78880903", "display_name": "Universidad de Huelva", "ror": "https://ror.org/03a1kt624", "country_code": "ES", "type": "education", "lineage": ["https://openalex.org/I78880903"]}], "countries": ["ES"], "is_corresponding": false, "raw_author_name": "Jacinto Mata", "raw_affiliation_strings": ["I2C Research Group Universidad de Huelva Huelva ES", "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain"], "raw_orcid": "https://orcid.org/0000-0001-5329-9622", "affiliations": [{"raw_affiliation_string": "I2C Research Group Universidad de Huelva Huelva ES", "institution_ids": ["https://openalex.org/I78880903"]}, {"raw_affiliation_string": "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain", "institution_ids": ["https://openalex.org/I78880903"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5043282222", "display_name": "Victoria Pach\u00f3n", "orcid": "https://orcid.org/0000-0003-0697-4044", "observed_orcids": ["https://orcid.org/0000-0003-0697-4044"]}, "institutions": [{"id": "https://openalex.org/I78880903", "display_name": "Universidad de Huelva", "ror": "https://ror.org/03a1kt624", "country_code": "ES", "type": "education", "lineage": ["https://openalex.org/I78880903"]}], "countries": ["ES"], "is_corresponding": false, "raw_author_name": "Victoria Pach\u00f3n", "raw_affiliation_strings": ["I2C Research Group Universidad de Huelva Huelva ES", "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain"], "raw_orcid": "https://orcid.org/0000-0003-0697-4044", "affiliations": [{"raw_affiliation_string": "I2C Research Group Universidad de Huelva Huelva ES", "institution_ids": ["https://openalex.org/I78880903"]}, {"raw_affiliation_string": "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain", "institution_ids": ["https://openalex.org/I78880903"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117273547", "display_name": "Ana Manovel", "orcid": "https://orcid.org/0000-0001-7015-170X", "observed_orcids": ["https://orcid.org/0000-0001-7015-170X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ana Manovel", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0001-7015-170X", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079271501", "display_name": "Manuel Jes\u00fas Ma\u00f1a L\u00f3pez", "orcid": "https://orcid.org/0000-0002-7551-2401", "observed_orcids": ["https://orcid.org/0000-0002-7551-2401"]}, "institutions": [{"id": "https://openalex.org/I78880903", "display_name": "Universidad de Huelva", "ror": "https://ror.org/03a1kt624", "country_code": "ES", "type": "education", "lineage": ["https://openalex.org/I78880903"]}], "countries": ["ES"], "is_corresponding": false, "raw_author_name": "Manuel J. Ma\u00f1a", "raw_affiliation_strings": ["I2C Research Group Universidad de Huelva Huelva ES", "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain"], "raw_orcid": "https://orcid.org/0000-0002-7551-2401", "affiliations": [{"raw_affiliation_string": "I2C Research Group Universidad de Huelva Huelva ES", "institution_ids": ["https://openalex.org/I78880903"]}, {"raw_affiliation_string": "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain", "institution_ids": ["https://openalex.org/I78880903"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5102024368", "display_name": "Manuel de la Villa", "orcid": "https://orcid.org/0000-0003-3464-2944", "observed_orcids": ["https://orcid.org/0000-0003-3464-2944"]}, "institutions": [{"id": "https://openalex.org/I78880903", "display_name": "Universidad de Huelva", "ror": "https://ror.org/03a1kt624", "country_code": "ES", "type": "education", "lineage": ["https://openalex.org/I78880903"]}], "countries": ["ES"], "is_corresponding": false, "raw_author_name": "Manuel de la Villa", "raw_affiliation_strings": ["I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain"], "raw_orcid": "https://orcid.org/0000-0003-3464-2944", "affiliations": [{"raw_affiliation_string": "I\u00b2C Research Group , University of Huelva , Campus El Carmen s/n , Huelva , Spain", "institution_ids": ["https://openalex.org/I78880903"]}]}], "abstract_inverted_index": {"BACKGROUND": [0], "Heart": [1], "failure": [2, 106], "with": [3], "preserved": [4], "ejection": [5], "fraction": [6], "(HFpEF)": [7], "is": [8, 91], "a": [9, 17, 31, 56, 75, 191], "major": [10], "clinical": [11, 47, 98, 122, 195, 208, 244], "manifestation": [12], "of": [13, 63, 83, 96, 104, 109, 177, 181, 214, 226, 239], "cardiac": [14, 110], "amyloidosis": [15], "(CA),": [16], "condition": [18], "frequently": [19], "underdiagnosed": [20], "due": [21], "to": [22, 60, 92, 100, 148, 235], "its": [23], "nonspecific": [24], "symptomatology.": [25], "Electronic": [26], "health": [27], "records": [28], "(EHRs)": [29], "offer": [30], "promising": [32], "avenue": [33], "for": [34, 79, 194], "supporting": [35], "early": [36, 102], "symptom": [37], "detection": [38, 82], "through": [39], "natural": [40], "language": [41, 219], "processing": [42], "(NLP).": [43], "However,": [44], "identifying": [45], "relevant": [46, 150], "cues": [48], "within": [49], "unstructured": [50, 206], "narratives,": [51], "particularly": [52], "in": [53, 86, 211, 242], "Spanish,": [54], "remains": [55], "significant": [57], "challenge": [58], "owing": [59], "the": [61, 80, 94, 154, 212, 224, 237], "scarcity": [62], "annotated": [64, 125], "corpora": [65], "and": [66, 73, 126, 139, 158, 179, 217, 232], "domain-specific": [67, 228], "models.": [68], "OBJECTIVE": [69], "This": [70], "study": [71], "proposes": [72], "evaluates": [74], "Transformer-based": [76, 198], "NLP": [77, 240], "framework": [78], "automated": [81], "HFpEF-related": [84, 203], "symptoms": [85, 204], "Spanish": [87, 121, 207], "EHRs.": [88], "Our": [89, 221], "objective": [90], "assess": [93], "feasibility": [95], "leveraging": [97], "narratives": [99], "support": [101], "identification": [103], "heart": [105], "phenotypes": [107], "suggestive": [108], "amyloidosis.": [111], "METHODS": [112], "A": [113], "novel": [114], "corpus": [115], "was": [116], "developed": [117], "from": [118, 205], "over": [119], "15,000": [120], "documents,": [123], "manually": [124], "validated": [127], "by": [128], "cardiology": [129], "experts.": [130], "Several": [131], "Transformer": [132], "architectures": [133], "were": [134], "benchmarked,": [135], "including": [136], "general-purpose,": [137], "biomedical-specialized,": [138], "long-document": [140], "models": [141, 162, 184, 199], "(Longformers),": [142], "under": [143, 153], "three": [144], "optimization": [145, 234], "strategies": [146], "tailored": [147, 233], "clinically": [149], "metrics:": [151], "area": [152], "curve": [155], "(AUC),": [156], "F1-score,": [157], "sensitivity.": [159], "RESULTS": [160], "All": [161], "achieved": [163, 185], "strong": [164], "performance": [165, 238], "(AUC": [166], ">": [167], "0.940).": [168], "The": [169], "best-performing": [170], "model,": [171], "Longformer": [172], "Biomedical-Clinical,": [173], "reached": [174], "an": [175], "AUC": [176], "0.987": [178], "F1-score": [180], "0.985.": [182], "Sensitivity-optimized": [183], "false": [186], "negative": [187], "rates": [188], "below": [189], "3%,": [190], "critical": [192], "threshold": [193], "applicability.": [196], "CONCLUSIONS": [197], "can": [200], "robustly": [201], "detect": [202], "texts,": [209], "even": [210], "presence": [213], "class": [215], "imbalance": [216], "complex": [218], "patterns.": [220], "findings": [222], "highlight": [223], "importance": [225], "combining": [227], "pretraining,": [229], "long-context": [230], "modeling,": [231], "enhance": [236], "systems": [241], "high-impact": [243], "applications.": [245]}, "primary_topic": {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.9442999958992004, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.9442999958992004, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11396", "display_name": "Artificial Intelligence in Healthcare", "score": 0.009800000116229057, "subfield": {"id": "https://openalex.org/subfields/3605", "display_name": "Health Information Management"}, "field": {"id": "https://openalex.org/fields/36", "display_name": "Health Professions"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.009399999864399433, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.2196/preprints.76433", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/preprints.76433", "pdf_url": "https://s3.ca-central-1.amazonaws.com/assets.jmir.org/assets/preprints/preprint-76433-submitted.pdf", "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417127631", "doi": "https://doi.org/10.26434/chemrxiv-2025-gmrdb", "title": "Learning to Generalize: Deep Models and Robust Benchmarks for Drug\u2013Target Affinity Prediction", "publication_year": 2025, "publication_date": "2025-12-08", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Agaaz Bansal", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I860003557", "display_name": "Punjab Engineering College", "ror": "https://ror.org/00bsj2955", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I860003557"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Agaaz Bansal", "raw_affiliation_strings": ["Punjab Engineering College"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Punjab Engineering College", "institution_ids": ["https://openalex.org/I860003557"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120724276", "display_name": "Milendra Kumar Turkar", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I119241673", "display_name": "Indian Institute of Technology Ropar", "ror": "https://ror.org/02qkhhn56", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I119241673"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Milendra Kumar Turkar", "raw_affiliation_strings": ["Indian Institute of Technology Ropar"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Indian Institute of Technology Ropar", "institution_ids": ["https://openalex.org/I119241673"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5146057389", "display_name": "Chirag Tayal", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I119241673", "display_name": "Indian Institute of Technology Ropar", "ror": "https://ror.org/02qkhhn56", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I119241673"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Chirag Tayal", "raw_affiliation_strings": ["Indian Institute of Technology Ropar", "Qatar Computing Research Institute"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Indian Institute of Technology Ropar", "institution_ids": ["https://openalex.org/I119241673"]}, {"raw_affiliation_string": "Qatar Computing Research Institute", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055826525", "display_name": "Raghvendra Mall", "orcid": "https://orcid.org/0000-0003-1779-3150", "observed_orcids": ["https://orcid.org/0000-0003-1779-3150"]}, "institutions": [{"id": "https://openalex.org/I119241673", "display_name": "Indian Institute of Technology Ropar", "ror": "https://ror.org/02qkhhn56", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I119241673"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Raghvendra Mall", "raw_affiliation_strings": ["Qatar Computing Research Institute", "Indian Institute of Technology Ropar"], "raw_orcid": "https://orcid.org/0000-0003-1779-3150", "affiliations": [{"raw_affiliation_string": "Qatar Computing Research Institute", "institution_ids": []}, {"raw_affiliation_string": "Indian Institute of Technology Ropar", "institution_ids": ["https://openalex.org/I119241673"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042455024", "display_name": "Sudipta Kumar Sinha", "orcid": "https://orcid.org/0000-0002-9568-5676", "observed_orcids": ["https://orcid.org/0000-0002-9568-5676"]}, "institutions": [{"id": "https://openalex.org/I119241673", "display_name": "Indian Institute of Technology Ropar", "ror": "https://ror.org/02qkhhn56", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I119241673"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Sudipta K Sinha", "raw_affiliation_strings": ["Indian Institute of Technology Ropar"], "raw_orcid": "https://orcid.org/0000-0002-9568-5676", "affiliations": [{"raw_affiliation_string": "Indian Institute of Technology Ropar", "institution_ids": ["https://openalex.org/I119241673"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5078080109", "display_name": "Sukrit Gupta", "orcid": "https://orcid.org/0000-0002-8974-8482", "observed_orcids": ["https://orcid.org/0000-0002-8974-8482"]}, "institutions": [{"id": "https://openalex.org/I119241673", "display_name": "Indian Institute of Technology Ropar", "ror": "https://ror.org/02qkhhn56", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I119241673"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Sukrit Gupta", "raw_affiliation_strings": ["Indian Institute of Technology Ropar"], "raw_orcid": "https://orcid.org/0000-0002-8974-8482", "affiliations": [{"raw_affiliation_string": "Indian Institute of Technology Ropar", "institution_ids": ["https://openalex.org/I119241673"]}]}], "abstract_inverted_index": {"Small-molecule": [0], "binding": [1, 12, 125], "to": [2, 59, 118, 167], "proteins": [3, 138], "drives": [4], "biological": [5], "processes": [6], "and": [7, 31, 55, 83, 85, 112, 122, 139, 144, 200], "underpins": [8], "drug": [9], "discovery,": [10], "with": [11], "affinity": [13, 69], "serving": [14], "as": [15], "a": [16, 100, 119, 130], "key": [17], "therapeutic": [18], "metric.": [19], "Traditional": [20], "3D": [21, 48], "structure-based": [22], "approaches": [23], "achieve": [24], "high": [25], "performance": [26, 56, 151], "but": [27, 50], "remain": [28], "computationally": [29], "expensive": [30], "limited": [32], "by": [33], "scarce": [34], "experimental": [35, 124], "data.": [36], "Deep": [37], "learning": [38, 91], "alternatives,": [39], "on": [40], "the": [41, 110, 135, 150, 153, 161, 170, 188, 201, 204], "other": [42], "hand,": [43], "capture": [44], "spatial": [45], "features": [46], "from": [47, 81, 95, 109, 165], "data": [49, 60, 131, 199], "risk": [51], "overfitting,": [52], "poor": [53], "generalization,": [54], "inflation": [57], "due": [58], "leakage.": [61], "We": [62, 98, 127, 147], "introduce": [63], "two": [64], "sequence-based": [65], "models": [66, 178], "for": [67, 203], "structure-free": [68], "prediction:": [70], "(1)": [71], "AffinityLM:": [72], "A": [73], "pretrained": [74], "biological\u2013chemical": [75], "language": [76], "model": [77], "using": [78], "concatenated": [79], "representations": [80], "FASTA": [82], "SMILES,": [84], "(2)": [86], "AffinityNet:": [87], "An": [88], "attention-based": [89], "architecture": [90], "contextual": [92], "drug\u2013target": [93], "dependencies": [94], "raw": [96], "sequences.": [97], "create": [99], "newly": [101], "curated": [102], "dataset": [103], "of": [104, 152, 160], "\\(\\sim\\)14,000": [105], "protein\u2013ligand": [106], "complexes,": [107], "pulled": [108], "Plas-20k": [111], "PDBbind-CN": [113], "datasets,": [114], "each": [115], "uniquely": [116], "mapped": [117], "PDB": [120], "ID": [121], "corresponding": [123], "affinity.": [126], "explicitly": [128], "define": [129], "split": [132], "that": [133, 149], "eliminates": [134], "overlap": [136], "between": [137], "ligands": [140], "across": [141], "train,": [142], "validation,": [143], "test": [145, 196], "sets.": [146, 197], "show": [148], "prior": [154], "benchmarks": [155], "drops": [156, 164], "significantly": [157], "(Pearson": [158], "correlation": [159], "best": [162], "benchmark": [163], "\\(0.74\\)": [166], "\\(0.67\\))": [168], "when": [169], "pervasive": [171], "data-leakage": [172], "problem": [173], "is": [174], "plugged.": [175], "The": [176, 198], "proposed": [177], "give": [179], "statistically": [180], "significant": [181], "improvements": [182], "(on": [183], "all": [184], "four": [185], "measures)": [186], "over": [187], "existing": [189], "baselines,": [190], "which": [191], "hold": [192], "under": [193], "independent,": [194], "out-of-distribution": [195], "code": [202], "work": [205], "are": [206], "available": [207], "at": [208], "\\url{https://github.com/AI4Med-Lab/affinitynet-benchmark}.": [209]}, "primary_topic": {"id": "https://openalex.org/T10211", "display_name": "Computational Drug Discovery Methods", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1703", "display_name": "Computational Theory and Mathematics"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10211", "display_name": "Computational Drug Discovery Methods", "score": 0.9980000257492065, "subfield": {"id": "https://openalex.org/subfields/1703", "display_name": "Computational Theory and Mathematics"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.0010999999940395355, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T12534", "display_name": "Protein Degradation and Inhibitors", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "doi:10.26434/chemrxiv-2025-gmrdb", "is_oa": true, "landing_page_url": "https://doi.org/10.26434/chemrxiv-2025-gmrdb", "pdf_url": null, "source": {"id": "https://openalex.org/S4393918830", "display_name": "ChemRxiv", "issn_l": "2573-2293", "issn": ["2573-2293"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406714995", "doi": "https://doi.org/10.1016/j.knosys.2025.113047", "title": "Enhancing knowledge retrieval with in-context learning and semantic search through generative AI", "publication_year": 2025, "publication_date": "2025-01-23", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5099008034", "display_name": "Mohammed-Khalil Ghali", "orcid": "https://orcid.org/0009-0003-5109-7084", "observed_orcids": ["https://orcid.org/0009-0003-5109-7084"]}, "institutions": [{"id": "https://openalex.org/I123946342", "display_name": "Binghamton University", "ror": "https://ror.org/008rmbt77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I123946342"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Mohammed-Khalil Ghali", "raw_affiliation_strings": ["School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA", "institution_ids": ["https://openalex.org/I123946342"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052443488", "display_name": "Abdelrahman Farrag", "orcid": "https://orcid.org/0000-0002-1897-0422", "observed_orcids": ["https://orcid.org/0000-0002-1897-0422"]}, "institutions": [{"id": "https://openalex.org/I123946342", "display_name": "Binghamton University", "ror": "https://ror.org/008rmbt77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I123946342"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Abdelrahman Farrag", "raw_affiliation_strings": ["School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA"], "raw_orcid": "https://orcid.org/0000-0002-1897-0422", "affiliations": [{"raw_affiliation_string": "School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA", "institution_ids": ["https://openalex.org/I123946342"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5047648692", "display_name": "Daehan Won", "orcid": "https://orcid.org/0000-0002-2566-8061", "observed_orcids": ["https://orcid.org/0000-0002-2566-8061"]}, "institutions": [{"id": "https://openalex.org/I123946342", "display_name": "Binghamton University", "ror": "https://ror.org/008rmbt77", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I123946342"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Daehan Won", "raw_affiliation_strings": ["School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Systems Science and Industrial Engineering, State University of New York at Binghamton, 4400 Vestal Pkwy, Binghamton, 13902, NY, USA", "institution_ids": ["https://openalex.org/I123946342"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5011199938", "display_name": "Yu Jin", "orcid": "https://orcid.org/0000-0001-9978-9037", "observed_orcids": ["https://orcid.org/0000-0001-9978-9037"]}, "institutions": [{"id": "https://openalex.org/I63190737", "display_name": "University at Buffalo, State University of New York", "ror": "https://ror.org/01y64my43", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I63190737"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Yu Jin", "raw_affiliation_strings": ["Department of Industrial and Systems Engineering, State University of New York at Buffalo, 210 Mary Talbert Way, Buffalo, 14260, NY, USA"], "raw_orcid": "https://orcid.org/0000-0001-9978-9037", "affiliations": [{"raw_affiliation_string": "Department of Industrial and Systems Engineering, State University of New York at Buffalo, 210 Mary Talbert Way, Buffalo, 14260, NY, USA", "institution_ids": ["https://openalex.org/I63190737"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.7515000104904175, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.7515000104904175, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.24120000004768372, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "score": 0.0007999999797903001, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.knosys.2025.113047", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.knosys.2025.113047", "pdf_url": null, "source": {"id": "https://openalex.org/S10169007", "display_name": "Knowledge-Based Systems", "issn_l": "0950-7051", "issn": ["0950-7051", "1872-7409"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-2", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Knowledge-Based Systems", "raw_type": "journal-article"}, "cited_by_count": 53, "is_retracted": false}, {"id": "https://openalex.org/W4415307344", "doi": "https://doi.org/10.48550/arxiv.2504.17432", "title": "Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs", "publication_year": 2025, "publication_date": "2025-04-24", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101333470", "display_name": "Tiancheng Gu", "orcid": "https://orcid.org/0009-0001-2302-246X", "observed_orcids": ["https://orcid.org/0009-0001-2302-246X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gu, Tiancheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061907296", "display_name": "Kai-Cheng Yang", "orcid": "https://orcid.org/0000-0001-6381-4026", "observed_orcids": ["https://orcid.org/0000-0001-6381-4026"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Kaicheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100531299", "display_name": "Ziyong Feng", "orcid": "https://orcid.org/0009-0007-8689-8366", "observed_orcids": ["https://orcid.org/0009-0007-8689-8366"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Feng, Ziyong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100740510", "display_name": "Xingjun Wang", "orcid": "https://orcid.org/0000-0001-5531-7273", "observed_orcids": ["https://orcid.org/0000-0001-5531-7273", "https://orcid.org/0000-0001-8206-2544"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Xingjun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103114439", "display_name": "Yanzhao Zhang", "orcid": "https://orcid.org/0000-0003-2894-4727", "observed_orcids": ["https://orcid.org/0000-0003-2894-4727", "https://orcid.org/0009-0003-6581-7783"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yanzhao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049484480", "display_name": "Dingkun Long", "orcid": "https://orcid.org/0000-0001-6570-9406", "observed_orcids": ["https://orcid.org/0000-0001-6570-9406"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Long, Dingkun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5104162468", "display_name": "Yingda Chen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Yingda", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076697411", "display_name": "Weidong Cai", "orcid": "https://orcid.org/0000-0003-3706-8896", "observed_orcids": ["https://orcid.org/0000-0003-3706-8896"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cai, Weidong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5073110676", "display_name": "Jiankang Deng", "orcid": "https://orcid.org/0000-0002-3709-6216", "observed_orcids": ["https://orcid.org/0000-0002-3709-6216"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Deng, Jiankang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"The": [0], "Contrastive": [1], "Language-Image": [2], "Pre-training": [3], "(CLIP)": [4], "framework": [5, 82], "has": [6], "become": [7], "a": [8, 79, 105], "widely": [9], "used": [10], "approach": [11, 164], "for": [12, 64, 90], "multimodal": [13, 67], "representation": [14, 135], "learning,": [15], "particularly": [16], "in": [17, 58, 175], "image-text": [18, 37], "retrieval": [19, 188, 195], "and": [20, 39, 144, 186, 192, 196, 213], "clustering.": [21], "However,": [22], "its": [23], "efficacy": [24], "is": [25], "constrained": [26], "by": [27], "three": [28], "key": [29], "limitations:": [30], "(1)": [31], "text": [32], "token": [33], "truncation,": [34], "(2)": [35], "isolated": [36], "encoding,": [38], "(3)": [40], "deficient": [41], "compositionality": [42], "due": [43], "to": [44, 86, 110, 131, 158], "bag-of-words": [45], "behavior.": [46], "While": [47], "recent": [48], "Multimodal": [49, 77], "Large": [50], "Language": [51], "Models": [52], "(MLLMs)": [53], "have": [54], "demonstrated": [55], "significant": [56], "advances": [57], "generalized": [59], "vision-language": [60], "understanding,": [61], "their": [62], "potential": [63], "learning": [65], "transferable": [66], "representations": [68, 89], "remains": [69], "underexplored.In": [70], "this": [71], "work,": [72], "we": [73, 98, 124, 138], "present": [74], "UniME": [75, 202], "(Universal": [76], "Embedding),": [78], "novel": [80], "two-stage": [81], "that": [83, 201], "leverages": [84], "MLLMs": [85], "learn": [87], "discriminative": [88, 101, 134, 168, 212], "diverse": [91], "downstream": [92, 176], "tasks.": [93, 177], "In": [94, 120], "the": [95, 112, 116, 121, 156, 183], "first": [96], "stage,": [97, 123], "perform": [99], "textual": [100], "knowledge": [102], "distillation": [103], "from": [104], "powerful": [106], "LLM-based": [107], "teacher": [108], "model": [109, 157], "enhance": [111], "embedding": [113], "capability": [114], "of": [115], "MLLM\u015b": [117], "language": [118], "component.": [119], "second": [122], "introduce": [125], "hard": [126, 148], "negative": [127, 142], "enhanced": [128], "instruction": [129], "tuning": [130], "further": [132], "advance": [133], "learning.": [136], "Specifically,": [137], "initially": [139], "mitigate": [140], "false": [141], "contamination": [143], "then": [145], "sample": [146], "multiple": [147, 187], "negatives": [149], "per": [150], "instance": [151], "within": [152], "each": [153], "batch,": [154], "forcing": [155], "focus": [159], "on": [160, 182], "challenging": [161], "samples.": [162], "This": [163], "not": [165], "only": [166], "improves": [167], "power": [169], "but": [170], "also": [171], "enhances": [172], "instruction-following": [173], "ability": [174], "We": [178], "conduct": [179], "extensive": [180], "experiments": [181], "MMEB": [184], "benchmark": [185], "tasks,": [189, 209], "including": [190], "short": [191], "long": [193], "caption": [194], "compositional": [197, 214], "retrieval.": [198], "Results": [199], "demonstrate": [200], "achieves": [203], "consistent": [204], "performance": [205], "improvement": [206], "across": [207], "all": [208], "exhibiting": [210], "superior": [211], "capabilities.": [215]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10627", "display_name": "Advanced Image and Video Retrieval Techniques", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.17432", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.17432", "pdf_url": "https://arxiv.org/pdf/2504.17432", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416842292", "doi": "https://doi.org/10.48550/arxiv.2507.00297", "title": "Natural language processing for African languages", "publication_year": 2025, "publication_date": "2025-06-30", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5088658365", "display_name": "David Ifeoluwa Adelani", "orcid": "https://orcid.org/0000-0002-0193-2083", "observed_orcids": ["https://orcid.org/0000-0002-0193-2083"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Adelani, David Ifeoluwa", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 64, 72, 80, 102, 120, 195, 209], "word": [3, 121, 145], "embeddings": [4, 122], "and": [5, 12, 40, 91, 107, 147, 163, 172, 217, 232], "language": [6, 153], "models": [7], "use": [8], "large-scale,": [9], "unlabelled": [10, 92], "data": [11, 25, 36, 87, 93, 131], "self-supervised": [13], "learning": [14, 234], "to": [15, 48, 170, 176], "boost": [16], "NLP": [17, 89, 196, 212], "performance.": [18], "Multilingual": [19], "models,": [20], "often": [21, 38], "trained": [22], "on": [23, 61, 95, 127, 133], "web-sourced": [24], "like": [26, 54], "Wikipedia,": [27], "face": [28], "challenges:": [29], "few": [30], "low-resource": [31, 164], "languages": [32, 53, 62, 71, 159, 179, 194, 208], "are": [33], "included,": [34], "their": [35], "is": [37], "noisy,": [39], "lack": [41], "of": [42, 82, 85, 116, 130, 136, 144, 184, 191], "labeled": [43], "datasets": [44, 204], "makes": [45], "it": [46], "hard": [47], "evaluate": [49], "performance": [50], "outside": [51], "high-resource": [52], "English.": [55], "In": [56], "this": [57, 73], "dissertation,": [58], "we": [59, 198], "focus": [60], "spoken": [63], "Sub-Saharan": [65], "Africa": [66], "where": [67], "all": [68], "the": [69, 83, 96, 100, 103, 114, 128, 134, 142, 148, 150, 189, 192], "indigenous": [70], "region": [74], "can": [75], "be": [76], "regarded": [77], "as": [78], "low-resourced": [79], "terms": [81], "availability": [84], "labelled": [86, 203], "for": [88, 158, 205], "tasks": [90], "found": [94], "web.": [97], "We": [98, 139, 166, 220], "analyse": [99], "noise": [101], "publicly": [104], "available": [105], "corpora,": [106], "curate": [108], "a": [109, 181], "high-quality": [110], "corpus,": [111], "demonstrating": [112], "that": [113], "quality": [115, 135], "semantic": [117], "representations": [118], "learned": [119], "does": [123], "not": [124], "only": [125], "depend": [126], "amount": [129, 183], "but": [132], "pre-training": [137, 162], "data.": [138], "demonstrate": [140], "empirically": [141], "limitations": [143], "embeddings,": [146], "opportunities": [149], "multilingual": [151, 174], "pre-trained": [152], "model": [154], "(PLM)": [155], "offers": [156], "especially": [157], "unseen": [160, 177], "during": [161], "scenarios.": [165], "further": [167], "study": [168], "how": [169], "adapt": [171], "specialize": [173], "PLMs": [175], "African": [178, 193, 207], "using": [180, 226], "small": [182], "monolingual": [185], "texts.": [186], "To": [187], "address": [188], "under-representation": [190], "research,": [197], "developed": [199], "large": [200], "scale": [201], "human-annotated": [202], "21": [206], "two": [210], "impactful": [211], "tasks:": [213], "named": [214], "entity": [215], "recognition": [216], "machine": [218], "translation.": [219], "conduct": [221], "an": [222], "extensive": [223], "empirical": [224], "evaluation": [225], "state-of-the-art": [227], "methods": [228], "across": [229], "supervised,": [230], "weakly-supervised,": [231], "transfer": [233], "settings.": [235]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7050999999046326, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7050999999046326, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.290800005197525, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.0017000000225380063, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2507.00297", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2507.00297", "pdf_url": "https://arxiv.org/pdf/2507.00297", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4407690465", "doi": "https://doi.org/10.48550/arxiv.2502.11196", "title": "How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training", "publication_year": 2025, "publication_date": "2025-02-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5003834274", "display_name": "Yixin Ou", "orcid": "https://orcid.org/0000-0001-7656-8004", "observed_orcids": ["https://orcid.org/0000-0001-7656-8004"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ou, Yixin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007559881", "display_name": "Yunzhi Yao", "orcid": "https://orcid.org/0000-0003-4491-0260", "observed_orcids": ["https://orcid.org/0000-0003-4491-0260"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yao, Yunzhi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5089259739", "display_name": "Ningyu Zhang", "orcid": "https://orcid.org/0000-0002-1970-0678", "observed_orcids": ["https://orcid.org/0000-0002-1970-0678"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ningyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Jin, Hui", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jin, Hui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102302090", "display_name": "Jiacheng Sun", "orcid": "https://orcid.org/0009-0004-3066-2328", "observed_orcids": ["https://orcid.org/0009-0004-3066-2328"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Jiacheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100930897", "display_name": "Shumin Deng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Deng, Shumin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103196797", "display_name": "Zhenguo Li", "orcid": "https://orcid.org/0000-0002-8492-3069", "observed_orcids": ["https://orcid.org/0000-0002-8492-3069"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Zhenguo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5102018239", "display_name": "Huajun Chen", "orcid": "https://orcid.org/0000-0001-5496-7442", "observed_orcids": ["https://orcid.org/0000-0001-5496-7442"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Huajun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Despite": [0], "exceptional": [1], "capabilities": [2], "in": [3, 14, 28, 119], "knowledge-intensive": [4], "tasks,": [5], "Large": [6], "Language": [7], "Models": [8], "(LLMs)": [9], "face": [10], "a": [11, 86, 101], "critical": [12], "gap": [13], "understanding": [15, 111], "how": [16, 22], "they": [17], "internalize": [18], "new": [19, 69, 116], "knowledge,": [20], "particularly": [21], "to": [23, 76, 92, 131], "structurally": [24], "embed": [25], "acquired": [26], "knowledge": [27, 40, 48, 70, 83, 98, 117], "their": [29], "neural": [30], "computations.": [31], "We": [32], "address": [33], "this": [34], "issue": [35], "through": [36], "the": [37, 66, 80, 95, 113], "lens": [38], "of": [39, 55, 68, 82, 97, 112, 115], "circuit": [41, 56], "evolution,": [42], "identifying": [43], "computational": [44], "subgraphs": [45], "that": [46], "facilitate": [47], "storage": [49], "and": [50, 136], "processing.": [51], "Our": [52], "systematic": [53], "analysis": [54], "evolution": [57, 81, 96], "throughout": [58], "continual": [59, 128], "pre-training": [60, 129], "reveals": [61], "several": [62], "key": [63], "findings:": [64], "(1)": [65], "acquisition": [67, 118], "is": [71], "influenced": [72], "by": [73], "its": [74], "relevance": [75], "pre-existing": [77], "knowledge;": [78], "(2)": [79], "circuits": [84, 99], "exhibits": [85], "distinct": [87], "phase": [88], "shift": [89], "from": [90], "formation": [91], "optimization;": [93], "(3)": [94], "follows": [100], "deep-to-shallow": [102], "pattern.": [103], "These": [104], "insights": [105], "not": [106], "only": [107], "advance": [108], "our": [109], "theoretical": [110], "mechanisms": [114], "LLMs,": [120], "but": [121], "also": [122], "provide": [123], "potential": [124], "implications": [125], "for": [126], "improving": [127], "strategies": [130], "enhance": [132], "model": [133], "performance.": [134], "Code": [135], "data": [137], "will": [138], "be": [139], "available": [140], "at": [141], "https://github.com/zjunlp/DynamicKnowledgeCircuits.": [142]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7562999725341797, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7562999725341797, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.21040000021457672, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.0024999999441206455, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.11196", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.11196", "pdf_url": "https://arxiv.org/pdf/2502.11196", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4412409612", "doi": "https://doi.org/10.54254/2755-2721/2025.po24899", "title": "A Survey on Pre-trained Language Models Based on Deep Learning: Technological Development and Applications", "publication_year": 2025, "publication_date": "2025-07-10", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yuansheng Lin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Yuansheng Lin", "raw_affiliation_strings": ["Capital University of Business, Beijing, China, 102218"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Capital University of Business, Beijing, China, 102218", "institution_ids": []}]}], "abstract_inverted_index": {"With": [0], "the": [1, 4, 9, 22, 41, 66, 83, 106, 116, 120, 127, 133], "advent": [2], "of": [3, 11, 24, 43, 69, 86, 97, 105, 109, 122, 129, 135, 145], "big": [5], "data": [6], "era": [7], "and": [8, 36, 54, 88, 94, 143, 156, 164], "enhancement": [10], "computing": [12], "capabilities,": [13], "deep": [14, 76], "learning": [15], "technologies": [16, 108], "have": [17, 38], "achieved": [18], "remarkable": [19], "breakthroughs": [20], "in": [21], "field": [23], "natural": [25], "language": [26, 31, 72, 130], "processing": [27], "(NLP).": [28], "Pre-trained": [29], "large": [30, 71], "models,": [32, 98, 124], "such": [33], "as": [34, 160, 162], "GPT": [35], "BERT,": [37], "significantly": [39, 125], "improved": [40], "performance": [42, 128], "various": [44], "NLP": [45], "tasks,": [46], "including": [47], "text": [48], "generation,": [49], "question-answering": [50], "systems,": [51], "sentiment": [52], "analysis,": [53], "machine": [55], "translation,": [56], "through": [57], "pre-training": [58, 84, 152], "on": [59, 75, 82], "large-scale": [60], "unsupervised": [61], "data.": [62], "This": [63], "paper": [64, 100], "reviews": [65], "latest": [67], "developments": [68], "pre-trained": [70, 110, 123], "models": [73], "based": [74], "learning,": [77], "with": [78], "a": [79, 91, 102], "particular": [80], "focus": [81], "methods": [85], "BERT": [87], "GPT.": [89], "Through": [90], "literature": [92], "review": [93], "comparative": [95], "analysis": [96], "this": [99], "provides": [101], "detailed": [103], "exploration": [104], "core": [107, 121], "models.": [111, 131], "The": [112], "study": [113], "finds": [114], "that": [115], "Transformer": [117], "architecture": [118], "is": [119], "enhancing": [126], "However,": [132], "expansion": [134], "model": [136, 154], "size": [137], "also": [138], "brings": [139], "increased": [140], "computational": [141], "costs": [142], "issues": [144], "interpretability.": [146], "Future": [147], "research": [148], "directions": [149], "include": [150], "efficient": [151], "methods,": [153], "compression": [155], "distillation,": [157], "multimodal": [158], "integration,": [159], "well": [161], "ethical": [163], "sustainability": [165], "issues.": [166]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9951000213623047, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9951000213623047, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.003599999938160181, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.54254/2755-2721/2025.po24899", "is_oa": true, "landing_page_url": "https://doi.org/10.54254/2755-2721/2025.po24899", "pdf_url": "https://www.ewadirect.com/proceedings/ace/article/view/24899/pdf", "source": {"id": "https://openalex.org/S4387281889", "display_name": "Applied and Computational Engineering", "issn_l": "2755-2721", "issn": ["2755-2721", "2755-273X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core"], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Applied and Computational Engineering", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4407213441", "doi": "https://doi.org/10.48550/arxiv.2502.03036", "title": "FuXi-$\u03b1$: Scaling Recommendation Model with Feature Interaction Enhanced Transformer", "publication_year": 2025, "publication_date": "2025-02-05", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113228420", "display_name": "Yufei Ye", "orcid": "https://orcid.org/0000-0001-8767-0848", "observed_orcids": ["https://orcid.org/0000-0001-8767-0848"]}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ye, Yufei", "raw_affiliation_strings": ["University of Science and Technology of China Hefei , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Science and Technology of China Hefei , China", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038446460", "display_name": "Wei-Feng Guo", "orcid": "https://orcid.org/0000-0003-0565-177X", "observed_orcids": ["https://orcid.org/0000-0003-0565-177X", "https://orcid.org/0000-0003-2115-3893"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Guo, Wei", "raw_affiliation_strings": ["Huawei Noah's Ark Lab Singapore , Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Noah's Ark Lab Singapore , Singapore", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5083772959", "display_name": "Jin Yao Chin", "orcid": "https://orcid.org/0000-0002-2909-3998", "observed_orcids": ["https://orcid.org/0000-0002-2909-3998"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chin, Jin Yao", "raw_affiliation_strings": ["Huawei Noah's Ark Lab Singapore , Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Noah's Ark Lab Singapore , Singapore", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5018288612", "display_name": "Hao Wang", "orcid": "https://orcid.org/0000-0002-7414-5240", "observed_orcids": ["https://orcid.org/0000-0002-7414-5240"]}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wang, Hao", "raw_affiliation_strings": ["University of Science and Technology of China Hefei , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Science and Technology of China Hefei , China", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102057858", "display_name": "Hong Zhu", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhu, Hong", "raw_affiliation_strings": ["Consumer Business Group , Huawei Shenzhen , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Consumer Business Group , Huawei Shenzhen , China", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5003528649", "display_name": "Xi Lin", "orcid": "https://orcid.org/0000-0001-8141-1482", "observed_orcids": ["https://orcid.org/0000-0001-8141-1482"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lin, Xi", "raw_affiliation_strings": ["Consumer Business Group , Huawei Shenzhen , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Consumer Business Group , Huawei Shenzhen , China", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5059668989", "display_name": "Yuyang Ye", "orcid": "https://orcid.org/0000-0002-1513-7814", "observed_orcids": ["https://orcid.org/0000-0002-1513-7814"]}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ye, Yuyang", "raw_affiliation_strings": ["University of Science and Technology of China Hefei , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Science and Technology of China Hefei , China", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5006207459", "display_name": "Yong Liu", "orcid": "https://orcid.org/0000-0002-1590-2029", "observed_orcids": ["https://orcid.org/0000-0002-1590-2029"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yong", "raw_affiliation_strings": ["Huawei Noah's Ark Lab Singapore , Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Noah's Ark Lab Singapore , Singapore", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5054330014", "display_name": "Ruiming Tang", "orcid": "https://orcid.org/0000-0002-9224-2431", "observed_orcids": ["https://orcid.org/0000-0002-9224-2431"]}, "institutions": [{"id": "https://openalex.org/I2250955327", "display_name": "Huawei Technologies (China)", "ror": "https://ror.org/00cmhce21", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I2250955327"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tang, Ruiming", "raw_affiliation_strings": ["Huawei Noah's Ark Lab Shenzhen , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Noah's Ark Lab Shenzhen , China", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085254654", "display_name": "Defu Lian", "orcid": "https://orcid.org/0000-0002-3507-9607", "observed_orcids": ["https://orcid.org/0000-0002-3507-9607"]}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lian, Defu", "raw_affiliation_strings": ["University of Science and Technology of China Hefei , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Science and Technology of China Hefei , China", "institution_ids": ["https://openalex.org/I126520041"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048237545", "display_name": "Enhong Chen", "orcid": "https://orcid.org/0000-0002-4835-4102", "observed_orcids": ["https://orcid.org/0000-0002-4835-4102"]}, "institutions": [{"id": "https://openalex.org/I126520041", "display_name": "University of Science and Technology of China", "ror": "https://ror.org/04c4dkn09", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I126520041", "https://openalex.org/I19820366"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chen, Enhong", "raw_affiliation_strings": ["University of Science and Technology of China Hefei , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Science and Technology of China Hefei , China", "institution_ids": ["https://openalex.org/I126520041"]}]}], "abstract_inverted_index": {"Inspired": [0], "by": [1, 70, 77], "scaling": [2], "laws": [3], "and": [4, 66, 127, 186], "large": [5], "language": [6], "models,": [7, 149], "research": [8], "on": [9, 96], "large-scale": [10, 27], "recommendation": [11, 24, 28, 38], "models": [12, 25, 29, 39, 61, 124], "has": [13, 199], "gained": [14], "significant": [15], "attention.": [16], "Recent": [17], "advancements": [18], "have": [19], "shown": [20], "that": [21, 122, 144], "expanding": [22], "sequential": [23, 37], "to": [26, 73, 110, 135], "can": [30], "be": [31], "an": [32, 117, 163], "effective": [33], "strategy.": [34], "Current": [35], "state-of-the-art": [36], "primarily": [40], "use": [41], "self-attention": [42], "mechanisms": [43], "for": [44], "explicit": [45], "feature": [46, 98, 138], "interactions": [47, 52], "among": [48], "items,": [49], "while": [50], "implicit": [51, 97, 137], "are": [53], "managed": [54], "through": [55], "Feed-Forward": [56], "Networks": [57], "(FFNs).": [58], "However,": [59], "these": [60, 112], "often": [62], "inadequately": [63], "integrate": [64], "temporal": [65], "positional": [67], "information,": [68], "either": [69], "adding": [71], "them": [72, 79], "attention": [74], "weights": [75], "or": [76], "blending": [78], "with": [80, 131, 150], "latent": [81], "representations,": [82], "which": [83, 172], "limits": [84], "their": [85], "expressive": [86], "power.": [87], "A": [88], "recent": [89], "model,": [90], "HSTU,": [91], "further": [92], "reduces": [93], "the": [94, 156, 168, 178, 191], "focus": [95], "interactions,": [99], "constraining": [100], "its": [101, 151], "performance.": [102], "We": [103], "propose": [104], "a": [105, 132, 174, 187], "new": [106], "model": [107, 115, 146, 157], "called": [108], "FuXi-$\u03b1$": [109], "address": [111], "issues.": [113], "This": [114], "introduces": [116], "Adaptive": [118], "Multi-channel": [119], "Self-attention": [120], "mechanism": [121], "distinctly": [123], "temporal,": [125], "positional,": [126], "semantic": [128], "features,": [129], "along": [130], "Multi-stage": [133], "FFN": [134], "enhance": [136], "interactions.": [139], "Our": [140, 197], "offline": [141], "experiments": [142], "demonstrate": [143], "our": [145], "outperforms": [147], "existing": [148], "performance": [152], "continuously": [153], "improving": [154], "as": [155], "size": [158], "increases.": [159], "Additionally,": [160], "we": [161], "conducted": [162], "online": [164], "A/B": [165], "test": [166], "within": [167], "Huawei": [169], "Music": [170], "app,": [171], "showed": [173], "$4.76\\%$": [175], "increase": [176, 189], "in": [177, 190], "average": [179, 192], "number": [180], "of": [181], "songs": [182], "played": [183], "per": [184, 195], "user": [185], "$5.10\\%$": [188], "listening": [193], "duration": [194], "user.": [196], "code": [198], "been": [200], "released": [201], "at": [202], "https://github.com/USTC-StarTeam/FuXi-alpha.": [203]}, "primary_topic": {"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12101", "display_name": "Advanced Bandit Algorithms Research", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.03036", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.03036", "pdf_url": "https://arxiv.org/pdf/2502.03036", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7154582043", "doi": "https://doi.org/10.48448/wcv3-1p84", "title": "Understanding Quantifier Scope with Large Language Models: How Many Children Climbed Trees?", "publication_year": 2025, "publication_date": "2025-06-18", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5133793129", "display_name": "Cognitive Science Society 2025", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cognitive Science Society 2025", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5140691345", "display_name": "Yan Cong", "orcid": "https://orcid.org/0000-0003-4571-9978", "observed_orcids": ["https://orcid.org/0000-0003-4571-9978"]}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Cong, Yan", "raw_affiliation_strings": ["Purdue University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082137441", "display_name": "Shaohua Fang", "orcid": "https://orcid.org/0000-0002-3342-5764", "observed_orcids": ["https://orcid.org/0000-0002-3342-5764"]}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Fang, Shaohua", "raw_affiliation_strings": ["Purdue University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University", "institution_ids": ["https://openalex.org/I219193219"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5064156388", "display_name": "Y Li", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I219193219", "display_name": "Purdue University West Lafayette", "ror": "https://ror.org/02dqehb95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I219193219"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Li, Yue", "raw_affiliation_strings": ["Purdue University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Purdue University", "institution_ids": ["https://openalex.org/I219193219"]}]}], "abstract_inverted_index": {"Sentences": [0], "with": [1, 66], "multiple": [2], "quantifiers": [3], "often": [4], "lead": [5], "to": [6, 20, 36, 44, 48], "interpretive": [7, 38], "ambiguities,": [8], "which": [9, 49], "can": [10], "vary": [11], "across": [12, 54], "languages.": [13], "This": [14], "study": [15], "adopts": [16], "a": [17], "cross-linguistic": [18], "approach": [19], "examine": [21], "how": [22, 115], "large": [23], "language": [24, 55, 111], "models": [25], "handle": [26], "quantifier": [27, 120, 132], "scope": [28, 121, 133], "interpretation": [29], "in": [30, 77, 87, 100, 130, 134], "English": [31, 74, 135], "and": [32, 75, 104, 136], "Chinese,": [33], "using": [34], "probabilities": [35], "assess": [37], "likelihood.": [39], "Humanlikeness": [40, 83], "scores": [41, 84], "were": [42], "used": [43], "quantify": [45], "the": [46], "extent": [47], "LLMs": [50, 61, 117], "emulate": [51], "human": [52, 67, 91, 119], "performance": [53], "groups.": [56], "Results": [57], "reveal": [58], "that": [59], "most": [60], "prefer": [62], "SS": [63], "interpretations,": [64], "aligning": [65], "tendencies,": [68], "while": [69], "only": [70], "some": [71], "differentiate": [72], "between": [73], "Chinese": [76], "IS": [78], "preferences,": [79], "reflecting": [80], "human-like": [81], "patterns.": [82], "highlight": [85], "variability": [86], "LLMs\u2019": [88], "approximation": [89], "of": [90], "behavior,": [92], "but": [93], "their": [94], "overall": [95], "potential": [96, 129], "is": [97], "notable.": [98], "Differences": [99], "model": [101], "architecture,": [102], "scale,": [103], "pretraining": [105], "data,": [106], "particularly": [107], "models\u2019": [108], "pre-training": [109], "data": [110], "background,": [112], "significantly": [113], "influence": [114], "closely": [116], "approximate": [118], "interpretations.": [122], "Deepseek-R1": [123], "was": [124], "also": [125], "explored": [126], "for": [127], "its": [128], "handling": [131], "Chinese.": [137]}, "primary_topic": {"id": "https://openalex.org/T10034", "display_name": "Syntax, Semantics, Linguistic Variation", "score": 0.73580002784729, "subfield": {"id": "https://openalex.org/subfields/1203", "display_name": "Language and Linguistics"}, "field": {"id": "https://openalex.org/fields/12", "display_name": "Arts and Humanities"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T10034", "display_name": "Syntax, Semantics, Linguistic Variation", "score": 0.73580002784729, "subfield": {"id": "https://openalex.org/subfields/1203", "display_name": "Language and Linguistics"}, "field": {"id": "https://openalex.org/fields/12", "display_name": "Arts and Humanities"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.2079000025987625, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.019700000062584877, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:escholarship.org:ark:/13030/qt1bw6j035", "is_oa": true, "landing_page_url": "https://escholarship.org/uc/item/1bw6j035", "pdf_url": "https://escholarship.org/content/qt1bw6j035/qt1bw6j035.pdf", "source": {"id": "https://openalex.org/S4306400115", "display_name": "eScholarship (California Digital Library)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I2801248553", "host_organization_name": "California Digital Library", "host_organization_lineage": ["https://openalex.org/I2801248553"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": "Proceedings of the Annual Meeting of the Cognitive Science Society, vol 47, iss 0", "raw_type": "article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4413188341", "doi": "https://doi.org/10.1109/lsp.2025.3597558", "title": "SVD-Guided Diffusion for Training-Free Low-Light Image Enhancement", "publication_year": 2025, "publication_date": "2025-01-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Jingi Kim", "orcid": "https://orcid.org/0009-0001-7991-5283", "observed_orcids": ["https://orcid.org/0009-0001-7991-5283"]}, "institutions": [{"id": "https://openalex.org/I24062138", "display_name": "Konkuk University", "ror": "https://ror.org/025h1m602", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I24062138"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Jingi Kim", "raw_affiliation_strings": ["Department of Electrical and Electronics Engineering, Konkuk University, Seoul, South Korea"], "raw_orcid": "https://orcid.org/0009-0001-7991-5283", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Electronics Engineering, Konkuk University, Seoul, South Korea", "institution_ids": ["https://openalex.org/I24062138"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5010430171", "display_name": "Wonjun Kim", "orcid": "https://orcid.org/0000-0001-5121-5931", "observed_orcids": ["https://orcid.org/0000-0001-5121-5931", "https://orcid.org/0009-0007-2192-800X"]}, "institutions": [{"id": "https://openalex.org/I24062138", "display_name": "Konkuk University", "ror": "https://ror.org/025h1m602", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I24062138"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Wonjun Kim", "raw_affiliation_strings": ["Department of Electrical and Electronics Engineering, Konkuk University, Seoul, South Korea"], "raw_orcid": "https://orcid.org/0000-0001-5121-5931", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Electronics Engineering, Konkuk University, Seoul, South Korea", "institution_ids": ["https://openalex.org/I24062138"]}]}], "abstract_inverted_index": {"Low-light": [0], "image": [1, 107, 193], "enhancement": [2, 194], "aims": [3], "to": [4, 38, 40, 55, 104, 115, 196], "improve": [5], "the": [6, 9, 31, 52, 60, 64, 68, 87, 117, 123, 127, 136, 148, 184, 189], "visibility": [7], "and": [8, 82, 110, 122], "contrast": [10], "of": [11, 51, 63, 120, 126, 139, 147, 160, 191], "images": [12], "captured": [13], "under": [14], "poor": [15], "lighting": [16, 140], "conditions": [17, 141], "while": [18], "preserving": [19], "contextual": [20], "details.": [21], "In": [22], "this": [23, 164], "context,": [24], "most": [25], "previous": [26], "methods": [27], "have": [28, 47], "relied": [29], "on": [30, 98, 173, 179], "paired": [32], "training": [33], "data,": [34], "which": [35, 151], "often": [36], "leads": [37], "overfitting": [39], "specific": [41], "data": [42], "distributions.": [43], "Although": [44], "recent": [45], "approaches": [46], "adopted": [48], "generative": [49, 124], "priors": [50], "diffusion": [53, 65, 95, 128], "model": [54, 66, 129], "avoid": [56], "such": [57], "learning": [58], "bias,": [59], "stochastic": [61], "nature": [62], "restricts": [67], "precise": [69], "control": [70], "over": [71], "luminance-related": [72], "features.": [73], "To": [74], "address": [75], "these": [76], "challenges,": [77], "we": [78, 113, 166], "propose": [79, 114], "a": [80, 93, 168, 174], "novel": [81], "training-free": [83, 198], "method": [84, 186], "that": [85, 101, 183], "integrates": [86], "Singular": [88], "Value": [89], "Decomposition": [90], "(SVD)": [91], "with": [92, 158], "pretrained": [94], "model.": [96, 176], "Based": [97], "our": [99, 132], "observation": [100], "SVD": [102, 121], "tends": [103], "separate": [105], "an": [106], "into": [108], "luminance": [109], "structural": [111], "components,": [112], "leverage": [116], "decomposition": [118], "capability": [119], "prior": [125], "simultaneously.": [130], "Specifically,": [131], "approach": [133], "effectively": [134], "guides": [135], "restoration": [137], "process": [138], "by": [142], "adaptively": [143], "combining": [144], "singular": [145], "values": [146], "intermediate": [149], "result,": [150], "is": [152], "obtained": [153], "from": [154], "each": [155], "denoising": [156], "step,": [157], "those": [159], "low-light": [161, 192], "input.": [162], "For": [163], "combination,": [165], "define": [167], "semantic-aware": [169], "scaling": [170], "scheme": [171], "based": [172], "vision-language": [175], "Experimental": [177], "results": [178], "benchmark": [180], "datasets": [181], "demonstrate": [182], "proposed": [185], "efficiently": [187], "improves": [188], "performance": [190], "compared": [195], "other": [197], "methods.": [199]}, "primary_topic": {"id": "https://openalex.org/T11019", "display_name": "Image Enhancement Techniques", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11019", "display_name": "Image Enhancement Techniques", "score": 0.9994999766349792, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10688", "display_name": "Image and Signal Denoising Methods", "score": 0.0003000000142492354, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11105", "display_name": "Advanced Image Processing Techniques", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1109/lsp.2025.3597558", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/lsp.2025.3597558", "pdf_url": null, "source": {"id": "https://openalex.org/S120629676", "display_name": "IEEE Signal Processing Letters", "issn_l": "1070-9908", "issn": ["1070-9908", "1558-2361"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-2", "norway-1"], "host_organization": "https://openalex.org/P4310319808", "host_organization_name": "Institute of Electrical and Electronics Engineers", "host_organization_lineage": ["https://openalex.org/P4310319808"], "host_organization_lineage_names": ["Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Signal Processing Letters", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4415036342", "doi": "https://doi.org/10.48550/arxiv.2505.20836", "title": "HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling", "publication_year": 2025, "publication_date": "2025-05-27", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yang, Hexiong", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210112150", "display_name": "Institute of Automation", "ror": "https://ror.org/022c3hy66", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}, {"id": "https://openalex.org/I4210165038", "display_name": "University of Chinese Academy of Sciences", "ror": "https://ror.org/05qbk4x57", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165038"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yang, Hexiong", "raw_affiliation_strings": ["NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "School of Advanced Interdisciplinary Science , University of Chinese Academy of Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210112150"]}, {"raw_affiliation_string": "School of Advanced Interdisciplinary Science , University of Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210165038"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050040890", "display_name": "Mingrui Chen", "orcid": "https://orcid.org/0009-0007-2702-2567", "observed_orcids": ["https://orcid.org/0009-0007-2702-2567", "https://orcid.org/0000-0002-6749-7926"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Mingrui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Huang, Huaibo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210112150", "display_name": "Institute of Automation", "ror": "https://ror.org/022c3hy66", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}, {"id": "https://openalex.org/I4210165038", "display_name": "University of Chinese Academy of Sciences", "ror": "https://ror.org/05qbk4x57", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165038"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Huang, Huaibo", "raw_affiliation_strings": ["NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "School of Artificial Intelligence , University of Chinese Academy of Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210112150"]}, {"raw_affiliation_string": "School of Artificial Intelligence , University of Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210165038"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5047230227", "display_name": "Junxian Duan", "orcid": "https://orcid.org/0000-0002-0218-6924", "observed_orcids": ["https://orcid.org/0000-0002-0218-6924"]}, "institutions": [{"id": "https://openalex.org/I4210112150", "display_name": "Institute of Automation", "ror": "https://ror.org/022c3hy66", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}, {"id": "https://openalex.org/I4210165038", "display_name": "University of Chinese Academy of Sciences", "ror": "https://ror.org/05qbk4x57", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165038"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Duan, Junxian", "raw_affiliation_strings": ["NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "School of Artificial Intelligence , University of Chinese Academy of Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210112150"]}, {"raw_affiliation_string": "School of Artificial Intelligence , University of Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210165038"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5077663149", "display_name": "Jie Cao", "orcid": "https://orcid.org/0000-0002-8209-3276", "observed_orcids": ["https://orcid.org/0000-0002-8209-3276"]}, "institutions": [{"id": "https://openalex.org/I4210112150", "display_name": "Institute of Automation", "ror": "https://ror.org/022c3hy66", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}, {"id": "https://openalex.org/I4210165038", "display_name": "University of Chinese Academy of Sciences", "ror": "https://ror.org/05qbk4x57", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165038"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Cao, Jie", "raw_affiliation_strings": ["NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "School of Artificial Intelligence , University of Chinese Academy of Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210112150"]}, {"raw_affiliation_string": "School of Artificial Intelligence , University of Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210165038"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100652063", "display_name": "Zhen Xian Zhou", "orcid": "https://orcid.org/0000-0003-0230-9688", "observed_orcids": ["https://orcid.org/0000-0003-0230-9688"]}, "institutions": [{"id": "https://openalex.org/I881766915", "display_name": "Nanjing University", "ror": "https://ror.org/01rxvg760", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I881766915"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhou, Zhen", "raw_affiliation_strings": ["Nanjing University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nanjing University", "institution_ids": ["https://openalex.org/I881766915"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5066692352", "display_name": "Ran He", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210112150", "display_name": "Institute of Automation", "ror": "https://ror.org/022c3hy66", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}, {"id": "https://openalex.org/I4210165038", "display_name": "University of Chinese Academy of Sciences", "ror": "https://ror.org/05qbk4x57", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I19820366", "https://openalex.org/I4210165038"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "He, Ran", "raw_affiliation_strings": ["NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "School of Artificial Intelligence , University of Chinese Academy of Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "NLPR&MAIS , Institute of Automation , Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210112150"]}, {"raw_affiliation_string": "School of Artificial Intelligence , University of Chinese Academy of Sciences", "institution_ids": ["https://openalex.org/I4210165038"]}]}], "abstract_inverted_index": {"Inspired": [0], "by": [1, 74], "the": [2, 11, 15, 28, 104, 107, 118, 127, 135, 146, 169, 202], "great": [3], "success": [4], "of": [5, 17, 30, 121, 137, 201], "Masked": [6], "Language": [7], "Modeling": [8], "(MLM)": [9], "in": [10, 27, 206], "natural": [12], "language": [13], "domain,": [14], "paradigm": [16], "self-supervised": [18], "pre-training": [19, 41], "and": [20, 92, 98, 110, 150], "fine-tuning": [21], "has": [22], "also": [23], "achieved": [24, 161], "remarkable": [25], "progress": [26], "field": [29], "DNA": [31], "sequence": [32], "modeling.": [33], "However,": [34], "previous": [35], "methods": [36], "often": [37], "relied": [38], "on": [39, 145, 173], "massive": [40], "data": [42], "or": [43], "large-scale": [44], "base": [45], "models": [46, 65, 155], "with": [47, 156], "huge": [48], "parameters,": [49, 158], "imposing": [50], "a": [51, 75, 83, 112, 198], "significant": [52], "computational": [53], "burden.": [54], "To": [55, 133], "address": [56], "this,": [57], "many": [58], "works": [59], "attempted": [60], "to": [61, 66, 116, 154], "use": [62], "more": [63, 96, 178, 188], "compact": [64], "achieve": [67], "similar": [68, 157], "outcomes": [69], "but": [70], "still": [71], "fell": [72], "short": [73], "considerable": [76], "margin.": [77], "In": [78], "this": [79], "work,": [80], "we": [81, 102, 141, 184], "propose": [82], "Hybrid": [84], "Architecture": [85], "Distillation": [86], "(HAD)": [87], "approach,": [88], "leveraging": [89], "both": [90], "distillation": [91, 170], "reconstruction": [93], "tasks": [94], "for": [95, 187], "efficient": [97], "effective": [99], "pre-training.": [100, 132], "Specifically,": [101], "employ": [103], "NTv2-500M": [105], "as": [106], "teacher": [108], "model": [109, 160, 172, 195], "devise": [111], "grouping": [113], "masking": [114], "strategy": [115], "align": [117], "feature": [119], "embeddings": [120], "visible": [122], "tokens": [123, 129], "while": [124], "concurrently": [125], "reconstructing": [126], "invisible": [128], "during": [130], "MLM": [131], "validate": [134], "effectiveness": [136], "our": [138, 159, 194], "proposed": [139], "method,": [140], "conducted": [142], "comprehensive": [143], "experiments": [144], "Nucleotide": [147], "Transformer": [148], "Benchmark": [149], "Genomic": [151], "Benchmark.": [152], "Compared": [153], "excellent": [162], "performance.": [163], "More": [164], "surprisingly,": [165], "it": [166], "even": [167], "surpassed": [168], "ceiling-teacher": [171], "some": [174], "sub-tasks,": [175], "which": [176, 191], "is": [177], "than": [179], "500": [180], "$\\times$": [181], "larger.": [182], "Lastly,": [183], "utilize": [185], "t-SNE": [186], "intuitive": [189], "visualization,": [190], "shows": [192], "that": [193], "can": [196], "gain": [197], "sophisticated": [199], "understanding": [200], "intrinsic": [203], "representation": [204], "pattern": [205], "genomic": [207], "sequences.": [208]}, "primary_topic": {"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.961899995803833, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, "topics": [{"id": "https://openalex.org/T12254", "display_name": "Machine Learning in Bioinformatics", "score": 0.961899995803833, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T12946", "display_name": "Fractal and DNA sequence analysis", "score": 0.015699999406933784, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T10015", "display_name": "Genomics and Phylogenetic Studies", "score": 0.010200000368058681, "subfield": {"id": "https://openalex.org/subfields/1312", "display_name": "Molecular Biology"}, "field": {"id": "https://openalex.org/fields/13", "display_name": "Biochemistry, Genetics and Molecular Biology"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2505.20836", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.20836", "pdf_url": "https://arxiv.org/pdf/2505.20836", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411989081", "doi": "https://doi.org/10.54254/2755-2721/2025.po24672", "title": "Open Set Domain Adaptation with Vision-language Models via Gradient-aware Separation", "publication_year": 2025, "publication_date": "2025-07-03", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101849513", "display_name": "Haoyang Chen", "orcid": "https://orcid.org/0000-0003-3141-2684", "observed_orcids": ["https://orcid.org/0000-0003-3141-2684"]}, "institutions": [{"id": "https://openalex.org/I200845125", "display_name": "Nanjing University of Information Science and Technology", "ror": "https://ror.org/02y0rxk19", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I200845125"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Haoyang Chen", "raw_affiliation_strings": ["Nanjing University of Information Science & Technology, Nan Jing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nanjing University of Information Science & Technology, Nan Jing, China", "institution_ids": ["https://openalex.org/I200845125"]}]}], "abstract_inverted_index": {"Open-Set": [0], "Domain": [1], "Adaptation": [2], "(OSDA)": [3], "confronts": [4], "the": [5, 96, 101, 130], "dual": [6], "challenge": [7], "of": [8, 98], "aligning": [9], "known-class": [10], "distributions": [11], "across": [12], "domains": [13, 78], "while": [14], "identifying": [15], "target-domain-specific": [16], "unknown": [17, 35], "categories.": [18], "Current": [19], "approaches": [20], "often": [21], "fail": [22], "to": [23, 40, 46], "leverage": [24], "semantic": [25, 72], "relationships": [26], "between": [27, 74], "modalities": [28], "and": [29, 76, 123], "struggle": [30], "with": [31], "error": [32], "accumulation": [33], "in": [34], "sample": [36], "detection.": [37], "We": [38], "propose": [39], "harness": [41], "Contrastive": [42], "Language-Image": [43], "Pretraining": [44], "(CLIP)": [45], "address": [47], "these": [48], "limitations": [49], "through": [50], "two": [51], "key": [52], "innovations:": [53], "1)": [54], "Prompt-driven": [55], "cross-domain": [56], "alignment:": [57], "Learnable": [58], "textual": [59], "prompts": [60], "conditioned": [61], "on": [62, 113], "domain": [63, 92], "discrepancy": [64], "metrics": [65], "dynamically": [66], "adapt": [67], "CLIP\u2019s": [68], "text": [69], "encoder,": [70], "enabling": [71], "consistency": [73], "source": [75], "target": [77], "without": [79], "explicit": [80], "unknown-class": [81], "supervision.": [82], "2)": [83], "Gradient-aware": [84], "open-set": [85], "separation:": [86], "A": [87], "gradient": [88, 110, 131], "analysis": [89], "module": [90], "quantifies": [91], "shift": [93], "by": [94], "comparing": [95], "L2-norm": [97], "gradients": [99], "from": [100], "learned": [102], "prompts,": [103], "where": [104], "known/unknown": [105], "samples": [106], "exhibit": [107], "statistically": [108], "distinct": [109], "behaviors.": [111], "Evaluations": [112], "Office-Home": [114], "show": [115], "that": [116], "our": [117], "method": [118], "consistently": [119], "outperforms": [120], "CLIP": [121], "baseline": [122], "standard": [124], "CoOp": [125], "baseline.": [126], "Ablation": [127], "studies": [128], "confirm": [129], "norm\u2019s": [132], "critical": [133], "role.": [134]}, "primary_topic": {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.54254/2755-2721/2025.po24672", "is_oa": true, "landing_page_url": "https://doi.org/10.54254/2755-2721/2025.po24672", "pdf_url": "https://www.ewadirect.com/proceedings/ace/article/view/24672/pdf", "source": {"id": "https://openalex.org/S4387281889", "display_name": "Applied and Computational Engineering", "issn_l": "2755-2721", "issn": ["2755-2721", "2755-273X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core"], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Applied and Computational Engineering", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4416418918", "doi": "https://doi.org/10.1016/j.csl.2025.101903", "title": "Using Knowledge Induction strategies: LLMs can do better in knowledge-driven dialogue tasks", "publication_year": 2025, "publication_date": "2025-11-20", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5085742376", "display_name": "Sisi Peng", "orcid": "https://orcid.org/0000-0003-3272-1016", "observed_orcids": ["https://orcid.org/0000-0003-3272-1016"]}, "institutions": [{"id": "https://openalex.org/I169689159", "display_name": "PLA Information Engineering University", "ror": "https://ror.org/00mm1qk40", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I169689159"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Sisi Peng", "raw_affiliation_strings": ["Information Engineering University, ZhengZhou, China"], "raw_orcid": "https://orcid.org/0000-0003-3272-1016", "affiliations": [{"raw_affiliation_string": "Information Engineering University, ZhengZhou, China", "institution_ids": ["https://openalex.org/I169689159"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100635256", "display_name": "Wenlin Zhang", "orcid": "https://orcid.org/0000-0002-6842-9722", "observed_orcids": ["https://orcid.org/0000-0002-6842-9722", "https://orcid.org/0009-0004-2400-8207"]}, "institutions": [{"id": "https://openalex.org/I169689159", "display_name": "PLA Information Engineering University", "ror": "https://ror.org/00mm1qk40", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I169689159"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wenlin Zhang", "raw_affiliation_strings": ["Information Engineering University, ZhengZhou, China", "Laboratory for Advanced Computing and Intelligence Engineering, ZhengZhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Information Engineering University, ZhengZhou, China", "institution_ids": ["https://openalex.org/I169689159"]}, {"raw_affiliation_string": "Laboratory for Advanced Computing and Intelligence Engineering, ZhengZhou, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100396892", "display_name": "Hao Zhang", "orcid": "https://orcid.org/0000-0002-3238-0066", "observed_orcids": ["https://orcid.org/0000-0002-3238-0066"]}, "institutions": [{"id": "https://openalex.org/I169689159", "display_name": "PLA Information Engineering University", "ror": "https://ror.org/00mm1qk40", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I169689159"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hao Zhang", "raw_affiliation_strings": ["Information Engineering University, ZhengZhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Information Engineering University, ZhengZhou, China", "institution_ids": ["https://openalex.org/I169689159"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111109197", "display_name": "Shunhang Li", "orcid": "https://orcid.org/0009-0005-5942-0928", "observed_orcids": ["https://orcid.org/0009-0005-5942-0928"]}, "institutions": [{"id": "https://openalex.org/I169689159", "display_name": "PLA Information Engineering University", "ror": "https://ror.org/00mm1qk40", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I169689159"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shunhang Li", "raw_affiliation_strings": ["Information Engineering University, ZhengZhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Information Engineering University, ZhengZhou, China", "institution_ids": ["https://openalex.org/I169689159"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5001488518", "display_name": "Dan Qu", "orcid": "https://orcid.org/0000-0001-9917-7794", "observed_orcids": ["https://orcid.org/0000-0001-9917-7794"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Dan Qu", "raw_affiliation_strings": ["Laboratory for Advanced Computing and Intelligence Engineering, ZhengZhou, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Laboratory for Advanced Computing and Intelligence Engineering, ZhengZhou, China", "institution_ids": []}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.9663000106811523, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.9663000106811523, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.027400000020861626, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.002199999988079071, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1016/j.csl.2025.101903", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.csl.2025.101903", "pdf_url": null, "source": {"id": "https://openalex.org/S91252481", "display_name": "Computer Speech & Language", "issn_l": "0885-2308", "issn": ["0885-2308", "1095-8363"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "erih-plus", "jufo-2", "norway-2"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Computer Speech &amp; Language", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406304848", "doi": "https://doi.org/10.1080/10903127.2025.2451209", "title": "Factors Associated with Abusive Head Trauma in Young Children Presenting to Emergency Medical Services Using a Large Language Model", "publication_year": 2025, "publication_date": "2025-01-13", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Allison Broad", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I51713134", "display_name": "University of Colorado Anschutz", "ror": "https://ror.org/03wmf1y16", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I51713134"]}, {"id": "https://openalex.org/I921990950", "display_name": "University of Colorado Denver", "ror": "https://ror.org/02hh7en24", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I921990950"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Allison Broad", "raw_affiliation_strings": ["University of Colorado School of Medicine", "University of Colorado School of Medicine, Aurora, CO"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Colorado School of Medicine", "institution_ids": ["https://openalex.org/I51713134", "https://openalex.org/I921990950"]}, {"raw_affiliation_string": "University of Colorado School of Medicine, Aurora, CO", "institution_ids": ["https://openalex.org/I51713134", "https://openalex.org/I921990950"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038978057", "display_name": "Xiao Luo", "orcid": "https://orcid.org/0000-0002-3649-9785", "observed_orcids": ["https://orcid.org/0000-0002-3649-9785"]}, "institutions": [{"id": "https://openalex.org/I115475287", "display_name": "Oklahoma State University", "ror": "https://ror.org/01g9vbr38", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I115475287"]}, {"id": "https://openalex.org/I4394709130", "display_name": "Indiana University School of Medicine", "ror": "https://ror.org/02ets8c94", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4394709130", "https://openalex.org/I592451"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xiao Luo", "raw_affiliation_strings": ["Department of Biostatistics and Health Data Science, Indiana University School of Medicine", "Department of Management Science & Information Systems, Oklahoma State University", "Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, IN", "Department of Management Science &amp; Information Systems, Oklahoma State University, Stillwater, OK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Biostatistics and Health Data Science, Indiana University School of Medicine", "institution_ids": ["https://openalex.org/I4394709130"]}, {"raw_affiliation_string": "Department of Management Science & Information Systems, Oklahoma State University", "institution_ids": ["https://openalex.org/I115475287"]}, {"raw_affiliation_string": "Department of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, IN", "institution_ids": ["https://openalex.org/I4394709130"]}, {"raw_affiliation_string": "Department of Management Science &amp; Information Systems, Oklahoma State University, Stillwater, OK", "institution_ids": ["https://openalex.org/I115475287"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091972050", "display_name": "Fattah Muhammad Tahabi", "orcid": "https://orcid.org/0000-0002-8498-278X", "observed_orcids": ["https://orcid.org/0000-0002-8498-278X"]}, "institutions": [{"id": "https://openalex.org/I115475287", "display_name": "Oklahoma State University", "ror": "https://ror.org/01g9vbr38", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I115475287"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Fattah Muhammad Tahabi", "raw_affiliation_strings": ["Department of Management Science & Information Systems, Oklahoma State University", "Department of Management Science &amp; Information Systems, Oklahoma State University, Stillwater, OK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Management Science & Information Systems, Oklahoma State University", "institution_ids": ["https://openalex.org/I115475287"]}, {"raw_affiliation_string": "Department of Management Science &amp; Information Systems, Oklahoma State University, Stillwater, OK", "institution_ids": ["https://openalex.org/I115475287"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067034539", "display_name": "Denise C. Abdoo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I51713134", "display_name": "University of Colorado Anschutz", "ror": "https://ror.org/03wmf1y16", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I51713134"]}, {"id": "https://openalex.org/I921990950", "display_name": "University of Colorado Denver", "ror": "https://ror.org/02hh7en24", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I921990950"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Denise Abdoo", "raw_affiliation_strings": ["Department of Pediatrics, University of Colorado School of Medicine", "Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Pediatrics, University of Colorado School of Medicine", "institution_ids": ["https://openalex.org/I51713134", "https://openalex.org/I921990950"]}, {"raw_affiliation_string": "Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO", "institution_ids": ["https://openalex.org/I51713134"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100393427", "display_name": "Zhan Zhang", "orcid": "https://orcid.org/0000-0002-9685-5753", "observed_orcids": ["https://orcid.org/0000-0002-9685-5753"]}, "institutions": [{"id": "https://openalex.org/I126863827", "display_name": "Pace University", "ror": "https://ror.org/047p7y759", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I126863827"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Zhan Zhang", "raw_affiliation_strings": ["Seidenberg School of Computer Science and Information Systems, Pace University", "Seidenberg School of Computer Science and Information Systems, Pace University, New York, NY"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Seidenberg School of Computer Science and Information Systems, Pace University", "institution_ids": ["https://openalex.org/I126863827"]}, {"raw_affiliation_string": "Seidenberg School of Computer Science and Information Systems, Pace University, New York, NY", "institution_ids": ["https://openalex.org/I126863827"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5029211654", "display_name": "Kathleen Adelgais", "orcid": "https://orcid.org/0000-0002-4405-0769", "observed_orcids": ["https://orcid.org/0000-0002-4405-0769"]}, "institutions": [{"id": "https://openalex.org/I51713134", "display_name": "University of Colorado Anschutz", "ror": "https://ror.org/03wmf1y16", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I51713134"]}, {"id": "https://openalex.org/I921990950", "display_name": "University of Colorado Denver", "ror": "https://ror.org/02hh7en24", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I921990950"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Kathleen Adelgais", "raw_affiliation_strings": ["Department of Pediatrics, University of Colorado School of Medicine", "Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Pediatrics, University of Colorado School of Medicine", "institution_ids": ["https://openalex.org/I51713134", "https://openalex.org/I921990950"]}, {"raw_affiliation_string": "Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO", "institution_ids": ["https://openalex.org/I51713134"]}]}], "abstract_inverted_index": {"OBJECTIVES:": [0], "Abusive": [1], "head": [2, 90, 101], "trauma": [3, 302, 321], "(AHT)": [4], "is": [5, 72], "a": [6, 73, 87, 156, 205, 215, 225, 240, 311], "leading": [7], "cause": [8], "of": [9, 15, 64, 77, 80, 84, 89, 169, 209, 217, 227, 230, 234, 242, 245, 248, 259, 301, 313, 320, 327], "death": [10], "in": [11, 49, 292, 324, 329], "young": [12, 65, 330], "children.": [13, 331], "Analyses": [14], "patient": [16], "characteristics": [17, 144], "presenting": [18], "to": [19, 27, 55, 60, 67, 138, 155, 165, 289], "Emergency": [20], "Medical": [21], "Services": [22], "(EMS)": [23], "are": [24, 194, 303], "often": [25], "limited": [26], "structured": [28, 50], "data": [29], "fields.": [30], "Artificial": [31], "Intelligence": [32], "(AI)": [33], "and": [34, 58, 108, 187, 207, 211, 232, 236, 253, 262, 282, 287], "Large": [35], "Language": [36, 124], "Models": [37], "(LLM)": [38], "may": [39, 315], "identify": [40, 139, 318], "rare": [41], "presentations": [42], "like": [43], "AHT": [44, 107, 328], "through": [45, 112], "factors": [46], "not": [47], "found": [48], "data.": [51], "Our": [52], "goal": [53], "was": [54, 104, 136, 175, 251, 255], "apply": [56], "AI": [57, 281], "LLM": [59, 130], "EMS": [61, 78, 293, 317], "narrative": [62], "documentation": [63], "children": [66, 81], "detect": [68, 166, 290], "AHT.": [69], "METHODS:": [70], "This": [71], "retrospective": [74], "cohort": [75], "study": [76], "transports": [79], "<36": [82], "months": [83], "age": [85], "with": [86, 132, 173, 214, 267, 298, 306, 310], "diagnosis": [88], "injury": [91, 102], "from": [92, 106], "the": [93, 182, 190, 221, 325], "2018-2019": [94], "ESO": [95], "Research": [96], "Data": [97], "Collaborative.": [98], "Non-abusive": [99], "closed": [100], "(NA-CHI)": [103], "distinguished": [105], "child": [109], "maltreatment": [110], "(AHT-CAN)": [111], "2": [113], "expert": [114, 133], "reviewers;": [115], "kappa": [116], "statistic": [117], "(k)": [118], "assessed": [119], "inter-rater": [120], "reliability.": [121], "A": [122, 257], "Natural": [123], "Processing": [125], "(NLP)": [126], "framework": [127, 154, 203], "using": [128, 177], "an": [129], "augmented": [131, 201, 309], "derived": [134], "n-grams": [135, 162, 237, 261, 314], "developed": [137], "AHT-CAN.": [140, 167, 307], "We": [141], "compared": [142], "test": [143], "(sensitivity,": [145], "specificity,": [146], "negative": [147], "predictive": [148], "value": [149], "(NPV))": [150], "between": [151], "this": [152], "NLP": [153, 202], "Generative": [157], "Pretrained": [158], "Transformer": [159], "(GPT)": [160], "or": [161], "only": [163], "models": [164], "Association": [168], "specific": [170], "word": [171], "tokens": [172], "AHT-CAN": [174, 268, 291], "analyzed": [176], "Pearson's": [178], "chi-square.": [179], "Area": [180, 188], "Under": [181, 189], "Receiver": [183], "Operator": [184], "Curve": [185, 192], "(AUROC)": [186], "Precision-Recall": [191], "(AUPRC)": [193], "also": [195], "reported.": [196], "RESULTS:": [197], "=": [198], "0.71).": [199], "The": [200], "had": [204, 224, 239], "specificity": [206, 229, 244, 288], "sensitivity": [208, 226, 241, 286], "72.4%": [210], "92.3%,": [212], "respectively": [213], "NPV": [216, 233, 247], "99.5%.": [218], "In": [219], "comparison,": [220], "GPT": [222], "model": [223], "69.2%,": [228], "97.1%": [231], "98.4%": [235], "alone": [238], "53.8%,": [243], "62.0%,": [246], "96.4%.": [249], "AUROC": [250], "0.91": [252], "AUPRC": [254], "0.52.": [256], "total": [258], "44": [260], "bi-grams": [263], "were": [264], "positively": [265], "associated": [266, 297, 305], "including": [269], "\"domestic,\"": [270], "\"various,\"": [271], "\"bruise,\"": [272], "\"cheek,\"": [273], "\"multiple,\"": [274], "\"doa,\"": [275], "\"not": [276], "respond,\"": [277], "\"see": [278], "EMS.\"": [279], "CONCLUSIONS:": [280], "LLMs": [283, 308], "have": [284], "high": [285], "free-text": [294], "narratives.": [295], "Words": [296], "physical": [299], "signs": [300, 319], "strongly": [304], "list": [312], "help": [316], "that": [322], "aid": [323], "detection": [326]}, "primary_topic": {"id": "https://openalex.org/T12235", "display_name": "Child Abuse and Related Trauma", "score": 0.9789999723434448, "subfield": {"id": "https://openalex.org/subfields/2735", "display_name": "Pediatrics, Perinatology and Child Health"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T12235", "display_name": "Child Abuse and Related Trauma", "score": 0.9789999723434448, "subfield": {"id": "https://openalex.org/subfields/2735", "display_name": "Pediatrics, Perinatology and Child Health"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T10426", "display_name": "Child Abuse and Trauma", "score": 0.005200000014156103, "subfield": {"id": "https://openalex.org/subfields/3203", "display_name": "Clinical Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.0015999999595806003, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.1080/10903127.2025.2451209", "is_oa": false, "landing_page_url": "https://doi.org/10.1080/10903127.2025.2451209", "pdf_url": null, "source": {"id": "https://openalex.org/S41500138", "display_name": "Prehospital Emergency Care", "issn_l": "1090-3127", "issn": ["1090-3127", "1545-0066"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-1", "medline", "norway-1"], "host_organization": "https://openalex.org/P4310320547", "host_organization_name": "Taylor & Francis", "host_organization_lineage": ["https://openalex.org/P4310320547", "https://openalex.org/P4310320449"], "host_organization_lineage_names": ["Taylor & Francis", "Informa"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Prehospital Emergency Care", "raw_type": "journal-article"}, "cited_by_count": 6, "is_retracted": false}, {"id": "https://openalex.org/W4417171295", "doi": "https://doi.org/10.48550/arxiv.2504.20609", "title": "WenyanGPT: A Large Language Model for Classical Chinese Tasks", "publication_year": 2025, "publication_date": "2025-04-29", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5068562966", "display_name": "Xinyu Yao", "orcid": "https://orcid.org/0000-0003-4554-5592", "observed_orcids": ["https://orcid.org/0000-0003-4554-5592"]}, "institutions": [{"id": "https://openalex.org/I145897649", "display_name": "Minzu University of China", "ror": "https://ror.org/0044e2g62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I145897649"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yao, Xinyu", "raw_affiliation_strings": ["Minzu University of China ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Minzu University of China ,", "institution_ids": ["https://openalex.org/I145897649"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100707456", "display_name": "Mengdi Wang", "orcid": "https://orcid.org/0000-0002-0214-2913", "observed_orcids": ["https://orcid.org/0000-0002-0214-2913"]}, "institutions": [{"id": "https://openalex.org/I145897649", "display_name": "Minzu University of China", "ror": "https://ror.org/0044e2g62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I145897649"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wang, Mengdi", "raw_affiliation_strings": ["Minzu University of China ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Minzu University of China ,", "institution_ids": ["https://openalex.org/I145897649"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100427253", "display_name": "Bo Chen", "orcid": "https://orcid.org/0000-0001-5151-9388", "observed_orcids": ["https://orcid.org/0000-0001-5151-9388"]}, "institutions": [{"id": "https://openalex.org/I145897649", "display_name": "Minzu University of China", "ror": "https://ror.org/0044e2g62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I145897649"]}, {"id": "https://openalex.org/I4210114290", "display_name": "China National Environmental Monitoring Center", "ror": "https://ror.org/026drga03", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I204710742", "https://openalex.org/I4210114290"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chen, Bo", "raw_affiliation_strings": ["Minzu University of China ,", "National Language Resources Monitoring & Research Center of Languages"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Minzu University of China ,", "institution_ids": ["https://openalex.org/I145897649"]}, {"raw_affiliation_string": "National Language Resources Monitoring & Research Center of Languages", "institution_ids": ["https://openalex.org/I4210114290"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5109291830", "display_name": "Xiaobing Zhao", "orcid": "https://orcid.org/0009-0007-1245-5490", "observed_orcids": ["https://orcid.org/0009-0007-1245-5490", "https://orcid.org/0009-0004-4413-6257"]}, "institutions": [{"id": "https://openalex.org/I145897649", "display_name": "Minzu University of China", "ror": "https://ror.org/0044e2g62", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I145897649"]}, {"id": "https://openalex.org/I4210114290", "display_name": "China National Environmental Monitoring Center", "ror": "https://ror.org/026drga03", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I204710742", "https://openalex.org/I4210114290"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhao, Xiaobing", "raw_affiliation_strings": ["Minzu University of China ,", "National Language Resources Monitoring & Research Center of Languages"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Minzu University of China ,", "institution_ids": ["https://openalex.org/I145897649"]}, {"raw_affiliation_string": "National Language Resources Monitoring & Research Center of Languages", "institution_ids": ["https://openalex.org/I4210114290"]}]}], "abstract_inverted_index": {"Classical": [0, 37, 46, 72, 97, 125], "Chinese,": [1, 31], "as": [2], "the": [3, 14, 57, 102, 122], "core": [4], "carrier": [5], "of": [6, 18, 124], "Chinese": [7, 47, 73, 98, 126], "culture,": [8], "plays": [9], "a": [10, 42, 62], "crucial": [11], "role": [12], "in": [13, 33, 95, 121], "inheritance": [15], "and": [16, 53, 109, 119], "study": [17], "ancient": [19], "literature.": [20], "However,": [21], "existing": [22], "natural": [23], "language": [24, 48, 64], "processing": [25], "models": [26], "primarily": [27], "optimize": [28], "for": [29, 45, 71], "Modern": [30], "resulting": [32], "inadequate": [34], "performance": [35], "on": [36, 56, 85], "Chinese.": [38], "This": [39], "paper": [40], "presents": [41], "comprehensive": [43], "solution": [44], "processing.": [49, 127], "By": [50], "continuing": [51], "pre-training": [52], "instruction": [54, 106], "fine-tuning": [55, 107], "LLaMA3-8B-Chinese": [58], "model,": [59, 65], "we": [60, 76], "construct": [61], "large": [63], "WenyanGPT,": [66], "which": [67], "is": [68], "specifically": [69], "designed": [70], "tasks.": [74, 99], "Additionally,": [75], "develop": [77], "an": [78], "evaluation": [79, 110], "benchmark": [80, 111], "dataset,": [81], "WenyanBENCH.": [82], "Experimental": [83], "results": [84], "WenyanBENCH": [86], "demonstrate": [87], "that": [88], "WenyanGPT": [89], "significantly": [90], "outperforms": [91], "current": [92], "advanced": [93], "LLMs": [94], "various": [96], "We": [100], "make": [101], "model's": [103], "training": [104], "data,": [105], "data\\footnote,": [108], "dataset": [112], "publicly": [113], "available": [114], "to": [115], "promote": [116], "further": [117], "research": [118], "development": [120], "field": [123]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9086999893188477, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9086999893188477, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.08839999884366989, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.00039999998989515007, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.20609", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.20609", "pdf_url": "https://arxiv.org/pdf/2504.20609", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416344029", "doi": "https://doi.org/10.48550/arxiv.2511.11315", "title": "LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models", "publication_year": 2025, "publication_date": "2025-11-14", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Ahad, Jawad Ibn", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ahad, Jawad Ibn", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109751297", "display_name": "Muhammad Rafsan Kabir", "orcid": "https://orcid.org/0009-0006-4431-3916", "observed_orcids": ["https://orcid.org/0009-0006-4431-3916"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kabir, Muhammad Rafsan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120309248", "display_name": "Robin Krambroeckers", "orcid": "https://orcid.org/0009-0008-5013-6922", "observed_orcids": ["https://orcid.org/0009-0008-5013-6922"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Krambroeckers, Robin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5027844735", "display_name": "Sifat Momen", "orcid": "https://orcid.org/0000-0001-8683-7247", "observed_orcids": ["https://orcid.org/0000-0001-8683-7247"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Momen, Sifat", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062072064", "display_name": "Nabeel Mohammed", "orcid": "https://orcid.org/0000-0002-7661-3570", "observed_orcids": ["https://orcid.org/0000-0002-7661-3570"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mohammed, Nabeel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5085599688", "display_name": "Shafin Rahman", "orcid": "https://orcid.org/0000-0002-0258-2150", "observed_orcids": ["https://orcid.org/0000-0002-0258-2150"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rahman, Shafin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Natural": [0], "Language": [1], "Processing": [2], "(NLP)": [3], "has": [4, 54], "transformed": [5], "the": [6, 60, 66, 74, 95], "financial": [7, 35, 52, 127, 149, 161], "industry,": [8], "enabling": [9], "advancements": [10], "in": [11, 126], "areas": [12], "such": [13, 136], "as": [14, 137], "textual": [15], "analysis,": [16, 40], "risk": [17, 46], "management,": [18], "and": [19, 27, 44, 62, 133, 152, 157], "forecasting.": [20], "Large": [21], "language": [22], "models": [23, 72, 159], "(LLMs)": [24], "like": [25], "BloombergGPT": [26], "FinMA": [28], "have": [29], "set": [30], "new": [31], "benchmarks": [32, 132], "across": [33], "various": [34], "NLP": [36, 128, 150], "tasks,": [37, 129], "including": [38], "sentiment": [39], "stock": [41], "movement": [42], "prediction,": [43], "credit": [45], "assessment.": [47], "Furthermore,": [48], "FinMA-ES,": [49], "a": [50, 89], "bilingual": [51], "LLM,": [53], "also": [55], "demonstrated": [56], "strong": [57, 124], "performance": [58], "using": [59], "FLARE": [61], "FLARE-ES": [63], "benchmarks.": [64], "However,": [65], "high": [67], "computational": [68, 115], "demands": [69], "of": [70, 76, 99], "these": [71], "limit": [73], "accessibility": [75], "many": [77], "organizations.": [78], "To": [79], "address": [80], "this,": [81], "we": [82], "propose": [83], "Layer-wise": [84], "Adaptive": [85], "Ensemble": [86], "Tuning": [87], "(LAET),": [88], "novel": [90], "strategy": [91], "that": [92], "selectively": [93], "fine-tunes": [94], "most": [96], "effective": [97], "layers": [98], "pre-trained": [100], "LLMs": [101, 135, 142], "by": [102], "analyzing": [103], "hidden": [104], "state": [105], "representations": [106], "while": [107, 117], "freezing": [108], "less": [109], "critical": [110], "layers.": [111], "LAET": [112], "significantly": [113], "reduces": [114], "overhead": [116], "enhancing": [118], "task-specific": [119], "performance.": [120], "Our": [121], "approach": [122], "shows": [123], "results": [125], "outperforming": [130], "existing": [131], "state-of-the-art": [134], "GPT-4,": [138], "even": [139], "with": [140, 155], "smaller": [141], "($\\sim$3B": [143], "parameters).": [144], "This": [145], "work": [146], "bridges": [147], "cutting-edge": [148], "research": [151], "real-world": [153], "deployment": [154], "efficient": [156], "scalable": [158], "for": [160], "applications.": [162]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9657999873161316, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9657999873161316, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11326", "display_name": "Stock Market Forecasting Methods", "score": 0.014999999664723873, "subfield": {"id": "https://openalex.org/subfields/1803", "display_name": "Management Science and Operations Research"}, "field": {"id": "https://openalex.org/fields/18", "display_name": "Decision Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.007199999876320362, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.11315", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.11315", "pdf_url": "https://arxiv.org/pdf/2511.11315", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417252840", "doi": "https://doi.org/10.48550/arxiv.2506.06606", "title": "Stacey: Promoting Stochastic Steepest Descent via Accelerated $\\ell_p$-Smooth Nonconvex Optimization", "publication_year": 2025, "publication_date": "2025-06-07", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Luo, Xinyu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Xinyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5002412726", "display_name": "Site Bai", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bai, Cedar Site", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5008288503", "display_name": "Bolian Li", "orcid": "https://orcid.org/0000-0002-1977-0764", "observed_orcids": ["https://orcid.org/0000-0002-1977-0764"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Bolian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5081378199", "display_name": "Petros Drineas", "orcid": "https://orcid.org/0000-0003-1994-8670", "observed_orcids": ["https://orcid.org/0000-0003-1994-8670"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Drineas, Petros", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5045967972", "display_name": "Ruqi Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ruqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5048046167", "display_name": "Brian Bullins", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bullins, Brian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"While": [0], "popular": [1, 88], "optimization": [2, 66], "methods": [3, 89], "such": [4], "as": [5], "SGD,": [6], "AdamW,": [7], "and": [8, 95, 104, 118, 123], "Lion": [9], "depend": [10], "on": [11, 90], "steepest": [12, 50], "descent": [13, 51], "updates": [14], "in": [15, 26, 32], "either": [16], "$\\ell_2$": [17], "or": [18], "$\\ell_\\infty$": [19], "norms,": [20], "there": [21], "remains": [22], "a": [23, 46], "critical": [24], "gap": [25], "handling": [27], "the": [28, 76, 121], "non-Euclidean": [29, 64, 126], "structure": [30], "observed": [31], "modern": [33], "deep": [34], "networks": [35], "training.": [36], "In": [37, 68], "this": [38, 42], "work,": [39], "we": [40, 81], "address": [41], "need": [43], "by": [44], "introducing": [45], "new": [47], "accelerated": [48], "$\\ell_p$": [49], "algorithm,": [52, 80], "called": [53], "Stacey,": [54], "which": [55], "uses": [56], "interpolated": [57], "primal-dual": [58], "iterate": [59], "sequences": [60], "to": [61, 70], "effectively": [62], "navigate": [63], "smooth": [65], "tasks.": [67], "addition": [69], "providing": [71], "novel": [72], "theoretical": [73], "guarantees": [74], "for": [75], "foundations": [77], "of": [78, 113, 125], "our": [79, 84], "empirically": [82], "compare": [83], "approach": [85], "against": [86], "these": [87], "tasks": [91], "including": [92], "image": [93], "classification": [94], "language": [96], "model": [97], "(LLM)": [98], "pretraining,": [99], "demonstrating": [100], "both": [101], "faster": [102], "convergence": [103], "higher": [105], "final": [106], "accuracy.": [107], "We": [108], "further": [109], "evaluate": [110], "different": [111], "values": [112], "$p$": [114], "across": [115], "various": [116], "models": [117], "datasets,": [119], "underscoring": [120], "importance": [122], "efficiency": [124], "approaches": [127], "over": [128], "standard": [129], "Euclidean": [130], "methods.": [131], "Code": [132], "can": [133], "be": [134], "found": [135], "at": [136], "https://github.com/xinyuluo8561/Stacey": [137], ".": [138]}, "primary_topic": {"id": "https://openalex.org/T11612", "display_name": "Stochastic Gradient Optimization Techniques", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11612", "display_name": "Stochastic Gradient Optimization Techniques", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10963", "display_name": "Advanced Optimization Algorithms Research", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/2612", "display_name": "Numerical Analysis"}, "field": {"id": "https://openalex.org/fields/26", "display_name": "Mathematics"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12535", "display_name": "Machine Learning and Data Classification", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2506.06606", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.06606", "pdf_url": "https://arxiv.org/pdf/2506.06606", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7114796869", "doi": "https://doi.org/10.48550/arxiv.2512.07865", "title": "Using Text-Based Life Trajectories from Swedish Register Data to Predict Residential Mobility with Pretrained Transformers", "publication_year": 2025, "publication_date": "2025-11-26", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Stark, Philipp", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Stark, Philipp", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Sopasakis, Alexandros", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sopasakis, Alexandros", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Hall, Ola", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hall, Ola", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Grillitsch, Markus", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Grillitsch, Markus", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0, 86], "transform": [1], "large-scale": [2], "Swedish": [3], "register": [4, 38, 119, 176], "data": [5, 16, 39, 120, 177], "into": [6, 45], "textual": [7], "life": [8, 59], "trajectories": [9, 60], "to": [10, 77], "address": [11], "two": [12], "long-standing": [13], "challenges": [14], "in": [15, 25, 54, 67, 187], "analysis:": [17], "high": [18], "cardinality": [19], "of": [20], "categorical": [21], "variables": [22], "and": [23, 49, 72, 95, 97, 101, 106, 127, 141, 147, 163], "inconsistencies": [24], "coding": [26], "schemes": [27], "over": [28], "time.": [29], "Leveraging": [30], "this": [31, 143], "uniquely": [32], "comprehensive": [33], "population": [34], "register,": [35], "we": [36], "convert": [37], "from": [40], "6.9": [41], "million": [42], "individuals": [43], "(2001-2013)": [44], "semantically": [46, 174], "rich": [47, 175], "texts": [48], "predict": [50], "individuals'": [51], "residential": [52], "mobility": [53], "later": [55], "years": [56], "(2013-2017).": [57], "These": [58], "combine": [61], "demographic": [62], "information": [63, 123], "with": [64, 138, 178], "annual": [65], "changes": [66], "residence,": [68], "work,": [69], "education,": [70], "income,": [71], "family": [73], "circumstances,": [74], "allowing": [75], "us": [76], "assess": [78], "how": [79], "effectively": [80, 110], "such": [81], "sequences": [82], "support": [83], "longitudinal": [84, 136, 185], "prediction.": [85], "compare": [87], "multiple": [88], "NLP": [89], "architectures": [90], "(including": [91], "LSTM,": [92], "DistilBERT,": [93], "BERT,": [94], "Qwen)": [96], "find": [98], "that": [99, 117, 150, 172], "sequential": [100], "transformer-based": [102], "models": [103, 181], "capture": [104], "temporal": [105], "semantic": [107], "structure": [108], "more": [109], "than": [111], "baseline": [112], "models.": [113], "The": [114], "results": [115], "show": [116], "textualized": [118], "preserves": [121], "meaningful": [122], "about": [124], "individual": [125], "pathways": [126], "supports": [128], "complex,": [129], "scalable": [130], "modeling.": [131], "Because": [132], "few": [133], "countries": [134], "maintain": [135], "microdata": [137], "comparable": [139], "coverage": [140], "precision,": [142], "dataset": [144], "enables": [145], "analyses": [146], "methodological": [148], "tests": [149], "would": [151], "be": [152], "difficult": [153], "or": [154], "impossible": [155], "elsewhere,": [156], "offering": [157], "a": [158], "rigorous": [159], "testbed": [160], "for": [161], "developing": [162], "evaluating": [164], "new": [165], "sequence-modeling": [166], "approaches.": [167], "Overall,": [168], "our": [169], "findings": [170], "demonstrate": [171], "combining": [173], "modern": [179], "language": [180], "can": [182], "substantially": [183], "advance": [184], "analysis": [186], "social": [188], "sciences.": [189]}, "primary_topic": {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.6054999828338623, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.6054999828338623, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11980", "display_name": "Human Mobility and Location-Based Analysis", "score": 0.21299999952316284, "subfield": {"id": "https://openalex.org/subfields/3313", "display_name": "Transportation"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.09000000357627869, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.48550/arxiv.2512.07865", "is_oa": true, "landing_page_url": "https://doi.org/10.48550/arxiv.2512.07865", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "Preprint"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416611615", "doi": "https://doi.org/10.48550/arxiv.2505.23380", "title": "UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning", "publication_year": 2025, "publication_date": "2025-05-29", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5007370280", "display_name": "Weijia Mao", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}, {"id": "https://openalex.org/I4405256866", "display_name": "ByteDance (China)", "ror": "https://ror.org/04m8av638", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I4405256866"]}], "countries": ["CN", "SG"], "is_corresponding": false, "raw_author_name": "Mao, Weijia", "raw_affiliation_strings": ["ByteDance", "Show Lab , National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "ByteDance", "institution_ids": ["https://openalex.org/I4405256866"]}, {"raw_affiliation_string": "Show Lab , National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5029181844", "display_name": "Zhenheng Yang", "orcid": "https://orcid.org/0000-0003-0303-5885", "observed_orcids": ["https://orcid.org/0000-0003-0303-5885"]}, "institutions": [{"id": "https://openalex.org/I4405256866", "display_name": "ByteDance (China)", "ror": "https://ror.org/04m8av638", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I4405256866"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yang, Zhenheng", "raw_affiliation_strings": ["ByteDance"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "ByteDance", "institution_ids": ["https://openalex.org/I4405256866"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5068937750", "display_name": "Mike Zheng Shou", "orcid": "https://orcid.org/0000-0002-7681-2166", "observed_orcids": ["https://orcid.org/0000-0002-7681-2166"]}, "institutions": [{"id": "https://openalex.org/I165932596", "display_name": "National University of Singapore", "ror": "https://ror.org/01tgyzw49", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I165932596"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Shou, Mike Zheng", "raw_affiliation_strings": ["Show Lab , National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Show Lab , National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}], "abstract_inverted_index": {"Unified": [0], "multimodal": [1], "large": [2], "language": [3], "models": [4, 22, 211], "such": [5], "as": [6, 80, 146], "Show-o": [7, 194, 204], "and": [8, 17, 28, 77, 110, 124, 173, 175, 195, 205, 210], "Janus": [9], "have": [10, 41], "achieved": [11], "strong": [12], "performance": [13], "across": [14], "both": [15], "generation": [16, 172], "understanding": [18, 112], "tasks.": [19], "However,": [20], "these": [21], "typically": [23], "rely": [24], "on": [25, 48, 88, 191], "large-scale": [26], "datasets": [27], "require": [29], "substantial": [30], "computation": [31], "during": [32, 156, 184], "the": [33, 70, 96, 103, 111, 132, 153, 169, 185], "pretraining": [34], "stage.": [35, 187], "In": [36, 57], "addition,": [37], "several": [38, 180], "post-training": [39, 65, 186], "methods": [40], "been": [42], "proposed,": [43], "but": [44, 166], "they": [45], "often": [46], "depend": [47], "external": [49, 90, 143], "data": [50, 82], "or": [51], "are": [52, 106, 114, 150], "limited": [53], "to": [54, 72, 99, 116, 130], "task-specific": [55], "customization.": [56], "this": [58], "work,": [59], "we": [60], "introduce": [61], "UniRL,": [62], "a": [63, 198], "self-improving": [64], "approach.": [66], "Our": [67], "approach": [68], "enables": [69, 95], "model": [71, 154], "generate": [73], "images": [74, 105], "from": [75], "prompts": [76], "use": [78], "them": [79], "training": [81, 148, 182], "in": [83, 215], "each": [84, 101], "iteration,": [85], "without": [86], "relying": [87], "any": [89], "image": [91, 144], "data.": [92], "Moreover,": [93], "it": [94, 140, 159, 177], "two": [97], "tasks": [98], "enhance": [100], "other:": [102], "generated": [104, 151], "used": [107, 115], "for": [108, 203, 207], "understanding,": [109], "results": [113], "supervise": [117], "generation.": [118], "We": [119, 188], "explore": [120], "supervised": [121], "fine-tuning": [122], "(SFT)": [123], "Group": [125], "Relative": [126], "Policy": [127], "Optimization": [128], "(GRPO)": [129], "optimize": [131], "models.": [133], "UniRL": [134, 190], "offers": [135], "three": [136], "key": [137], "advantages:": [138], "(1)": [139], "requires": [141, 178], "no": [142], "data,": [145], "all": [147], "samples": [149], "by": [152], "itself": [155], "training;": [157], "(2)": [158], "not": [160], "only": [161, 179], "improves": [162], "individual": [163], "task": [164], "performance,": [165], "also": [167], "reduces": [168], "imbalance": [170], "between": [171], "understanding;": [174], "(3)": [176], "additional": [181], "steps": [183], "evaluate": [189], "top": [192], "of": [193, 201], "Janus,": [196], "achieving": [197], "GenEval": [199], "score": [200], "0.77": [202], "0.65": [206], "Janus.": [208], "Code": [209], "will": [212], "be": [213], "released": [214], "https://github.com/showlab/UniRL.": [216]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "score": 0.000699999975040555, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2505.23380", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.23380", "pdf_url": "https://arxiv.org/pdf/2505.23380", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415981216", "doi": "https://doi.org/10.48550/arxiv.2504.04152", "title": "Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources", "publication_year": 2025, "publication_date": "2025-04-05", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100342798", "display_name": "Zihao Li", "orcid": "https://orcid.org/0000-0002-4382-577X", "observed_orcids": ["https://orcid.org/0000-0002-4382-577X", "https://orcid.org/0000-0002-1845-2860"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Zihao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007841686", "display_name": "Shaoxiong Ji", "orcid": "https://orcid.org/0000-0003-3281-8002", "observed_orcids": ["https://orcid.org/0000-0003-3281-8002"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ji, Shaoxiong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014129798", "display_name": "Hengyu Luo", "orcid": "https://orcid.org/0009-0006-0941-2126", "observed_orcids": ["https://orcid.org/0009-0006-0941-2126"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Hengyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5082417280", "display_name": "J\u00f6rg Tiedemann", "orcid": "https://orcid.org/0000-0003-3065-7989", "observed_orcids": ["https://orcid.org/0000-0003-3065-7989"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tiedemann, J\u00f6rg", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "exhibit": [4], "significant": [5], "disparities": [6], "in": [7], "performance": [8], "across": [9, 57], "languages,": [10, 105, 142], "primarily": [11], "benefiting": [12, 103], "high-resource": [13], "languages": [14, 59, 144, 152], "while": [15], "marginalizing": [16], "underrepresented": [17], "ones.": [18], "Continual": [19], "Pretraining": [20], "(CPT)": [21], "has": [22], "emerged": [23], "as": [24, 61, 136], "a": [25, 108], "promising": [26], "approach": [27], "to": [28, 117, 128, 180], "address": [29], "this": [30], "imbalance,": [31], "although": [32], "the": [33, 164, 171], "relative": [34], "effectiveness": [35], "of": [36, 166, 173], "monolingual,": [37], "bilingual,": [38], "and": [39, 64, 147, 150], "code-augmented": [40], "data": [41, 94], "strategies": [42], "remains": [43], "unclear.": [44], "This": [45], "study": [46], "systematically": [47], "evaluates": [48], "36": [49], "CPT": [50, 78, 96, 158, 184], "configurations": [51], "involving": [52], "three": [53, 73], "multilingual": [54, 80, 99, 167, 183], "base": [55], "models,": [56], "30+": [58], "categorized": [60], "altruistic,": [62], "selfish,": [63], "stagnant,": [65], "spanning": [66], "various": [67], "resource": [68], "levels.": [69], "Our": [70], "findings": [71], "reveal": [72], "major": [74], "insights:": [75], "(1)": [76], "Bilingual": [77], "improves": [79], "classification": [81, 100, 179], "but": [82, 106], "often": [83, 138], "causes": [84], "language": [85, 125, 178], "mixing": [86], "issues": [87], "during": [88, 95], "generation.": [89], "(2)": [90], "Including": [91], "programming": [92], "code": [93], "consistently": [97], "enhances": [98], "accuracy,": [101], "particularly": [102], "low-resource": [104], "introduces": [107], "trade-off": [109], "by": [110], "slightly": [111], "degrading": [112], "generation": [113], "quality.": [114], "(3)": [115], "Contrary": [116], "prior": [118], "work,": [119], "we": [120], "observe": [121], "substantial": [122], "deviations": [123], "from": [124], "classifications": [126], "according": [127], "their": [129], "impact": [130], "on": [131, 176], "cross-lingual": [132], "transfer:": [133], "Languages": [134], "classified": [135], "altruistic": [137], "negatively": [139], "affect": [140], "related": [141], "selfish": [143], "show": [145], "conditional": [146], "configuration-dependent": [148], "behavior,": [149], "stagnant": [151], "demonstrate": [153], "surprising": [154], "adaptability": [155], "under": [156], "certain": [157], "conditions.": [159], "These": [160], "nuanced": [161], "interactions": [162], "emphasize": [163], "complexity": [165], "representation": [168], "learning,": [169], "underscoring": [170], "importance": [172], "systematic": [174], "studies": [175], "generalizable": [177], "inform": [181], "future": [182], "strategies.": [185]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7148000001907349, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7148000001907349, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.16200000047683716, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.10490000247955322, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.04152", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.04152", "pdf_url": "https://arxiv.org/pdf/2504.04152", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406975875", "doi": "https://doi.org/10.48550/arxiv.2501.17840", "title": "Learning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning?", "publication_year": 2025, "publication_date": "2025-01-29", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5022655234", "display_name": "Pouya Pezeshkpour", "orcid": "https://orcid.org/0009-0002-7055-0035", "observed_orcids": ["https://orcid.org/0009-0002-7055-0035"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pezeshkpour, Pouya", "raw_affiliation_strings": ["Labs"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Labs", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5056213327", "display_name": "Estevam Rafael Hruschka Junior", "orcid": "https://orcid.org/0000-0003-1499-2808", "observed_orcids": ["https://orcid.org/0000-0003-1499-2808"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hruschka, Estevam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4], "demonstrated": [5], "remarkable": [6], "performance": [7], "on": [8, 50, 63, 95, 105], "various": [9], "tasks,": [10], "yet": [11], "their": [12], "ability": [13], "to": [14, 60, 75, 114], "extract": [15], "and": [16, 46, 55], "internalize": [17], "deeper": [18], "insights": [19], "from": [20], "domain-specific": [21], "datasets": [22], "remains": [23], "underexplored.": [24], "In": [25], "this": [26], "study,": [27], "we": [28, 57, 72], "investigate": [29], "how": [30, 77], "continual": [31, 79, 103], "pre-training": [32, 80, 104], "can": [33], "enhance": [34], "LLMs'": [35], "capacity": [36], "for": [37], "insight": [38, 70], "learning": [39], "across": [40], "three": [41], "distinct": [42], "forms:": [43], "declarative,": [44], "statistical,": [45], "probabilistic": [47], "insights.": [48, 97], "Focusing": [49], "two": [51, 64], "critical": [52], "domains:": [53], "medicine": [54], "finance,": [56], "employ": [58], "LoRA": [59], "train": [61], "LLMs": [62], "existing": [65], "datasets.": [66], "To": [67], "evaluate": [68], "each": [69], "type,": [71], "create": [73], "benchmarks": [74], "measure": [76], "well": [78], "helps": [81], "models": [82], "go": [83], "beyond": [84], "surface-level": [85], "knowledge.": [86], "We": [87], "also": [88], "assess": [89], "the": [90, 121], "impact": [91], "of": [92, 124], "document": [93], "modification": [94], "capturing": [96], "The": [98], "results": [99], "show": [100], "that,": [101], "while": [102], "original": [106], "documents": [107, 113], "has": [108], "a": [109], "marginal": [110], "effect,": [111], "modifying": [112], "retain": [115], "only": [116], "essential": [117], "information": [118], "significantly": [119], "enhances": [120], "insight-learning": [122], "capabilities": [123], "LLMs.": [125]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8422999978065491, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8422999978065491, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.15320000052452087, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.0008999999845400453, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2501.17840", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2501.17840", "pdf_url": "https://arxiv.org/pdf/2501.17840", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406032656", "doi": "https://doi.org/10.48550/arxiv.2501.00877", "title": "FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100683081", "display_name": "Bingyu Li", "orcid": "https://orcid.org/0000-0001-5925-1638", "observed_orcids": ["https://orcid.org/0000-0001-5925-1638"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Bingyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5088850494", "display_name": "Da Zhang", "orcid": "https://orcid.org/0000-0002-0790-9298", "observed_orcids": ["https://orcid.org/0000-0002-0790-9298"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Da", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079531245", "display_name": "Zhiyuan Zhao", "orcid": "https://orcid.org/0000-0002-1227-5058", "observed_orcids": ["https://orcid.org/0000-0002-1227-5058"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Zhiyuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014526931", "display_name": "Junyu Gao", "orcid": "https://orcid.org/0000-0002-8105-5497", "observed_orcids": ["https://orcid.org/0000-0002-8105-5497"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gao, Junyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100740143", "display_name": "Xuelong Li", "orcid": "https://orcid.org/0000-0002-0019-4197", "observed_orcids": ["https://orcid.org/0000-0002-0019-4197", "https://orcid.org/0009-0006-1021-6042"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xuelong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Open-vocabulary": [0], "segmentation": [1, 53, 82, 206], "aims": [2], "to": [3, 19, 28, 122, 135], "identify": [4], "and": [5, 9, 34, 59, 98, 117, 151, 162, 168, 185], "segment": [6], "specific": [7], "regions": [8], "objects": [10], "based": [11], "on": [12, 47, 203], "text-based": [13], "descriptions.": [14], "A": [15], "common": [16], "solution": [17], "is": [18, 106], "leverage": [20], "powerful": [21], "vision-language": [22], "models": [23], "(VLMs),": [24], "such": [25], "as": [26, 145], "CLIP,": [27, 128], "bridge": [29], "the": [30, 79, 124, 142], "gap": [31], "between": [32, 172], "vision": [33], "text": [35], "information.": [36], "However,": [37], "VLMs": [38, 65, 76], "are": [39], "typically": [40], "pretrained": [41], "for": [42, 94], "image-level": [43], "vision-text": [44], "alignment,": [45], "focusing": [46], "global": [48, 167], "semantic": [49, 132, 205], "features.": [50], "In": [51], "contrast,": [52], "tasks": [54], "require": [55], "fine-grained": [56, 95], "pixel-level": [57, 183], "alignment": [58, 97, 120, 126, 143, 184], "detailed": [60], "category": [61, 99, 137, 186], "boundary": [62, 100, 138, 170, 187], "information,": [63, 139, 188], "which": [64], "alone": [66], "cannot": [67], "provide.": [68], "As": [69], "a": [70, 91, 107, 113, 118], "result,": [71], "information": [72, 171], "extracted": [73], "directly": [74], "from": [75, 127, 160], "can't": [77], "meet": [78], "requirements": [80], "of": [81, 104], "tasks.": [83], "To": [84], "address": [85], "this": [86], "limitation,": [87], "we": [88, 140], "propose": [89, 152], "FGAseg,": [90], "model": [92], "designed": [93], "pixel-text": [96, 131], "supplementation.": [101], "The": [102], "core": [103], "FGAseg": [105, 180, 199], "Pixel-Level": [108], "Alignment": [109], "module": [110], "that": [111, 198], "employs": [112], "cross-modal": [114], "attention": [115], "mechanism": [116], "text-pixel": [119], "loss": [121], "refine": [123], "coarse-grained": [125], "achieving": [129], "finer-grained": [130], "alignment.": [133], "Additionally,": [134], "enrich": [136], "introduce": [141], "matrices": [144], "optimizable": [146], "pseudo-masks": [147], "during": [148], "forward": [149], "propagation": [150], "Category": [153], "Information": [154], "Supplementation": [155], "module.": [156], "These": [157], "pseudo-masks,": [158], "derived": [159], "cosine": [161], "convolutional": [163], "similarity,": [164], "provide": [165], "essential": [166], "local": [169], "different": [173], "categories.": [174], "By": [175], "combining": [176], "these": [177], "two": [178], "strategies,": [179], "effectively": [181], "enhances": [182], "addressing": [189], "key": [190], "challenges": [191], "in": [192], "open-vocabulary": [193, 204], "segmentation.": [194], "Extensive": [195], "experiments": [196], "demonstrate": [197], "outperforms": [200], "existing": [201], "methods": [202], "benchmarks.": [207]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.861299991607666, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.861299991607666, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.11330000311136246, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.01940000057220459, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2501.00877", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2501.00877", "pdf_url": "https://arxiv.org/pdf/2501.00877", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416587076", "doi": "https://doi.org/10.1021/acscatal.5c07050", "title": "Efficient Machine Learning for Yield Prediction in Transition Metal-Catalyzed meta -C(sp 2 )\u2013H Bond Activation and Other Reactions", "publication_year": 2025, "publication_date": "2025-11-24", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101679878", "display_name": "Supratim Ghosh", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I162827531", "display_name": "Indian Institute of Technology Bombay", "ror": "https://ror.org/02qyf5152", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I162827531"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Supratim Ghosh", "raw_affiliation_strings": ["Department of Chemistry", "Indian Institute of Technology Bombay", "Department of Chemistry, Indian Institute of Technology Bombay, Powai, Mumbai 400076, India"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Chemistry", "institution_ids": []}, {"raw_affiliation_string": "Indian Institute of Technology Bombay", "institution_ids": ["https://openalex.org/I162827531"]}, {"raw_affiliation_string": "Department of Chemistry, Indian Institute of Technology Bombay, Powai, Mumbai 400076, India", "institution_ids": ["https://openalex.org/I162827531"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103748629", "display_name": "Nupur Jain", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I162827531", "display_name": "Indian Institute of Technology Bombay", "ror": "https://ror.org/02qyf5152", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I162827531"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Nupur Jain", "raw_affiliation_strings": ["Department of Chemistry", "Indian Institute of Technology Bombay", "Department of Chemistry, Indian Institute of Technology Bombay, Powai, Mumbai 400076, India"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Chemistry", "institution_ids": []}, {"raw_affiliation_string": "Indian Institute of Technology Bombay", "institution_ids": ["https://openalex.org/I162827531"]}, {"raw_affiliation_string": "Department of Chemistry, Indian Institute of Technology Bombay, Powai, Mumbai 400076, India", "institution_ids": ["https://openalex.org/I162827531"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5018528585", "display_name": "Raghavan B. Sunoj", "orcid": "https://orcid.org/0000-0002-6484-2878", "observed_orcids": ["https://orcid.org/0000-0002-6484-2878"]}, "institutions": [{"id": "https://openalex.org/I162827531", "display_name": "Indian Institute of Technology Bombay", "ror": "https://ror.org/02qyf5152", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I162827531"]}], "countries": ["IN"], "is_corresponding": true, "raw_author_name": "Raghavan B. Sunoj", "raw_affiliation_strings": ["Center for Machine Intelligence and Data Science", "Department of Chemistry", "Indian Institute of Technology Bombay"], "raw_orcid": "https://orcid.org/0000-0002-6484-2878", "affiliations": [{"raw_affiliation_string": "Center for Machine Intelligence and Data Science", "institution_ids": []}, {"raw_affiliation_string": "Department of Chemistry", "institution_ids": []}, {"raw_affiliation_string": "Indian Institute of Technology Bombay", "institution_ids": ["https://openalex.org/I162827531"]}]}], "abstract_inverted_index": {"Developing": [0], "machine": [1], "learning": [2], "(ML)": [3], "models": [4, 56], "for": [5, 45, 65, 138, 230, 237], "yield": [6, 66, 155, 242, 253], "prediction": [7, 243], "of": [8, 31, 52, 100, 109, 115, 165, 170, 175, 226, 252], "chemical": [9, 42], "reactions": [10, 46, 88, 108], "has": [11], "emerged": [12], "as": [13, 58, 263], "an": [14], "important": [15], "use": [16], "case": [17], "scenario": [18], "in": [19, 211, 241, 296], "very": [20], "recent": [21], "years.": [22], "In": [23], "this": [24], "space,": [25], "reaction": [26, 80, 283, 297], "datasets": [27], "present": [28], "a": [29, 79, 94, 98, 132, 172, 187, 223, 249, 288], "range": [30], "challenges": [32], "mostly": [33], "stemming": [34], "from": [35, 90, 180, 197], "imbalance": [36], "and": [37, 124, 134, 142, 208, 233, 281, 290], "sparsity.": [38], "Herein,": [39], "we": [40, 129, 184], "consider": [41], "language": [43, 54], "representations": [44], "to": [47, 71, 97, 204], "tap": [48], "into": [49], "the": [50, 59, 116, 121, 125, 144, 158, 166, 181, 198, 219, 231, 238, 245, 257, 266, 270], "potential": [51], "natural": [53], "processing": [55], "such": [57, 74], "ULMFiT": [60], "(Universal": [61], "Language": [62], "Model": [63], "Fine-Tuning)": [64], "prediction,": [67], "which": [68, 151, 201], "is": [69, 202, 260], "customized": [70], "work": [72], "across": [73], "distribution": [75, 127], "settings.": [76], "We": [77], "contribute": [78], "dataset": [81, 117, 189], "with": [82, 218, 248], "more": [83, 153, 209], "than": [84, 157], "860": [85], "manually": [86], "curated": [87], "collected": [89], "literature": [91], "spanning": [92], "over": [93, 269], "decade,": [95], "belonging": [96], "family": [99], "catalytic": [101], "meta": [102], "-C(sp": [103], "2": [104], ")\u2013H": [105], "bond": [106], "activation": [107], "high": [110], "contemporary": [111], "importance.": [112], "Taking": [113], "cognizance": [114], "size,": [118], "skewness": [119], "toward": [120], "higher": [122], "yields,": [123], "sparse": [126], "characteristics,": [128], "developed": [130], "(i)": [131], "time-": [133], "resource-efficient": [135], "pretraining": [136, 168, 188], "strategy": [137], "downstream": [139], "transfer": [140], "learning,": [141], "(ii)": [143], "CFR": [145, 216, 258], "(classification": [146], "followed": [147], "by": [148, 193, 265], "regression)": [149], "model,": [150], "provided": [152], "accurate": [154], "predictions": [156], "traditional": [159], "direct": [160], "regression": [161], "(DR)": [162], "methods.": [163], "Instead": [164], "prevailing": [167], "practice": [169], "using": [171, 194], "large": [173], "number": [174], "unlabeled": [176], "molecules": [177], "(1.4": [178], "million)": [179, 192], "ChEMBL": [182], "dataset,": [183], "first": [185], "created": [186], "SSP1": [190], "(0.11": [191], "substructure-based": [195], "mining": [196], "PubChem": [199], "database,": [200], "found": [203], "be": [205], "equally": [206], "effective": [207], "time-efficient": [210], "offering": [212], "enhanced": [213], "performance.": [214], "The": [215], "model": [217, 259, 286], "ULMFiT-SSP1": [220], "regressor": [221], "achieved": [222], "notable": [224], "RMSE": [225], "8.40": [227], "\u00b1": [228, 235], "0.12": [229], "CFR-major": [232], "6.48": [234], "0.29": [236], "CFR-minor": [239], "class": [240, 250], "on": [244, 273], "title": [246], "reaction,": [247], "boundary": [251], "at": [254], "53%.": [255], "Furthermore,": [256], "highly": [261], "generalizable": [262], "evidenced": [264], "significant": [267], "improvement": [268], "previous": [271], "benchmarks": [272], "Buchwald\u2013Hartwig": [274], "coupling,": [275, 277, 280], "Suzuki": [276], "nickel-catalyzed": [278], "C\u2013O": [279], "USPTO": [282], "datasets.": [284], "Our": [285], "provides": [287], "scalable": [289], "efficient": [291], "framework": [292], "that": [293], "can": [294], "assist": [295], "discovery.": [298]}, "primary_topic": {"id": "https://openalex.org/T11948", "display_name": "Machine Learning in Materials Science", "score": 0.8324999809265137, "subfield": {"id": "https://openalex.org/subfields/2505", "display_name": "Materials Chemistry"}, "field": {"id": "https://openalex.org/fields/25", "display_name": "Materials Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11948", "display_name": "Machine Learning in Materials Science", "score": 0.8324999809265137, "subfield": {"id": "https://openalex.org/subfields/2505", "display_name": "Materials Chemistry"}, "field": {"id": "https://openalex.org/fields/25", "display_name": "Materials Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10211", "display_name": "Computational Drug Discovery Methods", "score": 0.13830000162124634, "subfield": {"id": "https://openalex.org/subfields/1703", "display_name": "Computational Theory and Mathematics"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13297", "display_name": "History and advancements in chemistry", "score": 0.003000000026077032, "subfield": {"id": "https://openalex.org/subfields/1606", "display_name": "Physical and Theoretical Chemistry"}, "field": {"id": "https://openalex.org/fields/16", "display_name": "Chemistry"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1021/acscatal.5c07050", "is_oa": false, "landing_page_url": "https://doi.org/10.1021/acscatal.5c07050", "pdf_url": null, "source": {"id": "https://openalex.org/S37391459", "display_name": "ACS Catalysis", "issn_l": "2155-5435", "issn": ["2155-5435"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-3", "ki-jl-2", "norway-2"], "host_organization": "https://openalex.org/P4310320006", "host_organization_name": "American Chemical Society", "host_organization_lineage": ["https://openalex.org/P4310320006"], "host_organization_lineage_names": ["American Chemical Society"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "ACS Catalysis", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4416233349", "doi": "https://doi.org/10.2196/preprints.87129", "title": "Evaluating LLM Alignment on Personality Inference from Real-World Interview Data (Preprint)", "publication_year": 2025, "publication_date": "2025-11-13", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101818972", "display_name": "Jianfeng Zhu", "orcid": "https://orcid.org/0000-0003-4779-3696", "observed_orcids": ["https://orcid.org/0000-0003-4779-3696"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jianfeng Zhu", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0003-4779-3696", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5095084660", "display_name": "Julina Maharjan", "orcid": "https://orcid.org/0009-0003-3390-0259", "observed_orcids": ["https://orcid.org/0009-0003-3390-0259"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Julina Maharjan", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0003-3390-0259", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100406134", "display_name": "Xinyu Li", "orcid": "https://orcid.org/0009-0002-9905-5230", "observed_orcids": ["https://orcid.org/0009-0002-9905-5230"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xinyu Li", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5081383028", "display_name": "Karin G. Coifman", "orcid": "https://orcid.org/0000-0002-2372-0081", "observed_orcids": ["https://orcid.org/0000-0002-2372-0081"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Karin G. Coifman", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-2372-0081", "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5103270436", "display_name": "Ruoming Jin", "orcid": "https://orcid.org/0000-0003-1895-4243", "observed_orcids": ["https://orcid.org/0000-0003-1895-4243"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ruoming Jin", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0003-1895-4243", "affiliations": []}], "abstract_inverted_index": {"UNSTRUCTURED": [0], "Large": [1], "Language": [2], "Models": [3], "(LLMs)": [4], "are": [5], "increasingly": [6], "deployed": [7], "in": [8, 40], "roles": [9], "requiring": [10], "nuanced": [11], "psychological": [12, 165], "understanding,": [13], "such": [14, 35], "as": [15], "emotional": [16], "support": [17], "agents,": [18], "counselors,": [19], "and": [20, 111, 124, 127, 136, 149, 199, 208], "decision-making": [21], "assistants.": [22], "However,": [23], "their": [24], "ability": [25], "to": [26, 121], "interpret": [27], "human": [28, 197], "personality": [29, 68, 151, 176], "traits,": [30], "a": [31, 83], "critical": [32], "aspect": [33], "of": [34, 63, 160, 192], "applications,": [36], "remains": [37], "unexplored,": [38], "particularly": [39], "ecologically": [41], "valid": [42], "conversational": [43], "settings.": [44], "While": [45], "prior": [46], "work": [47, 202], "has": [48], "simulated": [49], "LLM": [50], "\u201dpersonas\u201d": [51], "using": [52, 130], "discrete": [53], "Big": [54, 94], "Five": [55, 95], "labels": [56], "on": [57, 180, 203], "social": [58], "media": [59], "data,": [60], "the": [61, 157, 190], "alignment": [62, 159], "LLMs": [64, 104, 162, 194], "with": [65, 91, 114, 163, 195], "continuous,": [66], "ground-truth": [67, 150], "assessments": [69], "derived": [70], "from": [71, 133], "natural": [72], "interactions": [73], "is": [74], "largely": [75], "unexamined.": [76], "To": [77], "address": [78], "this": [79, 99], "gap,": [80], "we": [81, 101], "introduce": [82], "novel": [84], "benchmark": [85], "comprising": [86], "semi-structured": [87], "interview": [88], "transcripts": [89], "paired": [90], "validated": [92, 164], "continuous": [93], "trait": [96], "scores.": [97], "Using": [98], "dataset,": [100], "systematically": [102], "evaluate": [103], "performance": [105], "across": [106], "three": [107], "paradigms:": [108], "(1)": [109], "zero-shot": [110], "chain-of-thought": [112], "prompting": [113, 168], "GPT-4.1": [115], "Mini,": [116], "(2)": [117], "LoRA-based": [118], "fine-tuning": [119], "applied": [120], "both": [122], "RoBERTa": [123], "Meta-LLaMA": [125], "architectures.": [126], "(3)": [128], "regression": [129], "static": [131], "embedding": [132], "pretrained": [134], "BERT": [135], "OpenAI\u2019s": [137], "text-embedding-3-small.": [138], "Our": [139], "results": [140], "reveal": [141], "that": [142, 175], "all": [143], "Pearson": [144], "correlations": [145], "between": [146], "model": [147], "predictions": [148], "traits": [152], "remain": [153], "below": [154], "0.26,": [155], "highlighting": [156], "limited": [158], "current": [161], "constructs.": [166], "Chain-of-thought": [167], "offers": [169], "minimal": [170], "gains": [171], "over": [172], "zero-shot,": [173], "suggesting": [174], "inference": [177], "relies": [178], "more": [179], "latent": [181], "semantic": [182], "representation": [183], "than": [184], "explicit": [185], "reasoning.": [186], "These": [187], "findings": [188], "underscore": [189], "challenges": [191], "aligning": [193], "complex": [196], "attributes": [198], "motivate": [200], "future": [201], "trait-specific": [204], "prompting,": [205], "context-aware": [206], "modeling,": [207], "alignment-oriented": [209], "fine-tuning.": [210]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5253999829292297, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5253999829292297, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12488", "display_name": "Mental Health via Writing", "score": 0.09969999641180038, "subfield": {"id": "https://openalex.org/subfields/3207", "display_name": "Social Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T11040", "display_name": "Personality Traits and Psychology", "score": 0.06710000336170197, "subfield": {"id": "https://openalex.org/subfields/3203", "display_name": "Clinical Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.2196/preprints.87129", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/preprints.87129", "pdf_url": null, "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415082526", "doi": "https://doi.org/10.48550/arxiv.2503.00572", "title": "LoR2C : Low-Rank Residual Connection Adaptation for Parameter-Efficient Fine-Tuning", "publication_year": 2025, "publication_date": "2025-03-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5013699342", "display_name": "Jiancheng Zhao", "orcid": "https://orcid.org/0009-0001-3561-1456", "observed_orcids": ["https://orcid.org/0009-0001-3561-1456"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Jiancheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Yu, Xingda", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yu, Xingda", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062948751", "display_name": "Yuxiang Zhang", "orcid": "https://orcid.org/0000-0002-3256-042X", "observed_orcids": ["https://orcid.org/0000-0002-3256-042X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yuxiang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5084415556", "display_name": "Zhen Chao Yang", "orcid": "https://orcid.org/0000-0002-7728-916X", "observed_orcids": ["https://orcid.org/0000-0002-7728-916X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Zhen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"In": [0], "recent": [1], "years,": [2], "pretrained": [3], "large": [4], "language": [5, 14, 142, 146], "models": [6], "have": [7, 38], "demonstrated": [8], "outstanding": [9], "performance": [10, 127], "across": [11], "various": [12], "natural": [13, 141, 145], "processing": [15], "tasks.": [16], "However,": [17], "full-parameter": [18], "fine-tuning": [19, 34, 70, 96, 170], "methods": [20, 35], "require": [21], "adjusting": [22], "all": [23], "model": [24, 87, 126], "parameters,": [25, 44], "leading": [26], "to": [27], "immense": [28], "computational": [29], "resource": [30], "demands.": [31], "Although": [32], "parameter-efficient": [33, 69, 169], "like": [36], "LoRA": [37], "significantly": [39, 156], "reduced": [40], "the": [41, 54, 86, 93, 102], "number": [42, 94], "of": [43, 95, 113], "they": [45], "still": [46], "face": [47], "challenges": [48], "such": [49], "as": [50], "gradient": [51, 103], "vanishing": [52, 104], "and": [53, 117, 125, 133, 144, 152], "potential": [55], "for": [56], "further": [57, 121], "parameter": [58, 123, 129, 158], "reduction.": [59], "To": [60], "address": [61], "these": [62], "issues,": [63], "this": [64, 107], "paper": [65, 108], "proposes": [66], "a": [67], "novel": [68], "method": [71], "called": [72], "LoR2C": [73, 78, 151], "(Low-Rank": [74], "Residual": [75], "Connection": [76], "Adaptation).": [77], "introduces": [79], "residual": [80], "connections": [81], "with": [82], "low-rank": [83], "matrices": [84], "within": [85], "layers,": [88], "which": [89], "not": [90], "only": [91], "reduces": [92], "parameters": [97], "but": [98], "also": [99], "effectively": [100], "alleviates": [101], "problem.": [105], "Additionally,": [106], "presents": [109], "three": [110], "optimization": [111], "variants": [112, 120, 155], "LoR2C:": [114], "ShareLoR2C,": [115], "MergeLoR2C,": [116], "InjectLoR2C.": [118], "These": [119], "improve": [122], "efficiency": [124], "through": [128], "sharing,": [130], "module": [131], "merging,": [132], "injection": [134], "mechanisms,": [135], "respectively.": [136], "Experimental": [137], "results": [138], "on": [139], "multiple": [140], "understanding": [143], "generation": [147], "tasks": [148], "demonstrate": [149], "that": [150], "its": [153], "optimized": [154], "reduce": [157], "overhead": [159], "while": [160], "maintaining": [161], "or": [162], "even": [163], "improving": [164], "performance,": [165], "outperforming": [166], "existing": [167], "mainstream": [168], "methods.Our": [171], "code": [172], "is": [173], "publicly": [174], "available": [175], "at": [176], "https://github.com/Oblivioniss/LoR2C.": [177]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.663100004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.663100004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.3019999861717224, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.01810000091791153, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2503.00572", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.00572", "pdf_url": "https://arxiv.org/pdf/2503.00572", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416125918", "doi": "https://doi.org/10.48550/arxiv.2504.04221", "title": "Evaluating Graphical Perception with Multimodal LLMs", "publication_year": 2025, "publication_date": "2025-04-05", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Nguyen, Rami Huu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nguyen, Rami Huu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Maeda, Kenichi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Maeda, Kenichi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5098490628", "display_name": "Mahsa Geshvadi", "orcid": "https://orcid.org/0009-0006-0768-526X", "observed_orcids": ["https://orcid.org/0009-0006-0768-526X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Geshvadi, Mahsa", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5062859783", "display_name": "Daniel Haehn", "orcid": "https://orcid.org/0000-0001-9144-3461", "observed_orcids": ["https://orcid.org/0000-0001-9144-3461"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Haehn, Daniel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Multimodal": [0], "Large": [1], "Language": [2], "Models": [3], "(MLLMs)": [4], "have": [5], "remarkably": [6], "progressed": [7], "in": [8, 19, 88, 93], "analyzing": [9], "and": [10, 47, 52, 64, 67, 110], "understanding": [11, 105], "images.": [12], "Despite": [13], "these": [14], "advancements,": [15], "accurately": [16], "regressing": [17], "values": [18], "charts": [20], "remains": [21], "an": [22, 104], "underexplored": [23], "area": [24], "for": [25], "MLLMs.": [26], "For": [27], "visualization,": [28], "how": [29], "do": [30], "MLLMs": [31, 83, 108], "perform": [32], "when": [33, 112], "applied": [34, 113], "to": [35, 70, 102, 114], "graphical": [36, 77], "perception": [37], "tasks?": [38], "Our": [39, 59, 79], "paper": [40], "investigates": [41], "this": [42], "question": [43], "by": [44], "reproducing": [45], "Cleveland": [46], "McGill's": [48], "seminal": [49], "1984": [50], "experiment": [51], "comparing": [53], "it": [54], "against": [55], "human": [56, 76, 85], "task": [57, 86], "performance.": [58], "study": [60], "primarily": [61], "evaluates": [62], "fine-tuned": [63], "pretrained": [65], "models": [66], "zero-shot": [68], "prompting": [69], "determine": [71], "if": [72], "they": [73], "closely": [74], "match": [75], "perception.": [78], "findings": [80], "highlight": [81, 96], "that": [82], "outperform": [84], "performance": [87], "some": [89], "cases": [90], "but": [91], "not": [92], "others.": [94], "We": [95], "the": [97], "results": [98], "of": [99, 106], "all": [100], "experiments": [101], "foster": [103], "where": [107], "succeed": [109], "fail": [111], "data": [115], "visualization.": [116]}, "primary_topic": {"id": "https://openalex.org/T10799", "display_name": "Data Visualization and Analytics", "score": 0.7407000064849854, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10799", "display_name": "Data Visualization and Analytics", "score": 0.7407000064849854, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.24009999632835388, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.003100000089034438, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.04221", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.04221", "pdf_url": "https://arxiv.org/pdf/2504.04221", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415936372", "doi": "https://doi.org/10.48550/arxiv.2511.00269", "title": "FedReplay: A Feature Replay Assisted Federated Transfer Learning Framework for Efficient and Privacy-Preserving Smart Agriculture", "publication_year": 2025, "publication_date": "2025-10-31", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100408764", "display_name": "Long Li", "orcid": "https://orcid.org/0000-0002-1939-5941", "observed_orcids": ["https://orcid.org/0000-0002-1939-5941"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Long", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100454275", "display_name": "Jiajia Li", "orcid": "https://orcid.org/0000-0001-8158-3970", "observed_orcids": ["https://orcid.org/0000-0001-8158-3970"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Jiajia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100319482", "display_name": "Dong Chen", "orcid": "https://orcid.org/0000-0003-2018-1120", "observed_orcids": ["https://orcid.org/0000-0003-2018-1120"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Dong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5077083196", "display_name": "Lina Pu", "orcid": "https://orcid.org/0000-0002-5663-1501", "observed_orcids": ["https://orcid.org/0000-0002-5663-1501"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pu, Lina", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5027637869", "display_name": "Haibo Yao", "orcid": "https://orcid.org/0000-0003-2967-0051", "observed_orcids": ["https://orcid.org/0000-0003-2967-0051"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yao, Haibo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5006023502", "display_name": "Yanbo Huang", "orcid": "https://orcid.org/0000-0002-1409-8868", "observed_orcids": ["https://orcid.org/0000-0002-1409-8868"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Huang, Yanbo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Accurate": [0], "classification": [1, 155], "plays": [2], "a": [3, 56, 62, 72, 101, 119], "pivotal": [4], "role": [5], "in": [6], "smart": [7], "agriculture,": [8], "enabling": [9], "applications": [10], "such": [11], "as": [12], "crop": [13], "monitoring,": [14], "fruit": [15], "recognition,": [16], "and": [17, 40, 45, 96, 182, 194], "pest": [18], "detection.": [19], "However,": [20], "conventional": [21], "centralized": [22], "training": [23, 91], "often": [24], "requires": [25], "large-scale": [26, 92], "data": [27, 44, 117], "collection,": [28], "which": [29, 165], "raises": [30], "privacy": [31, 143], "concerns,": [32], "while": [33, 145], "standard": [34], "federated": [35, 57, 98, 175, 190], "learning": [36, 58, 176, 191], "struggles": [37], "with": [38, 71, 189], "non-independent": [39], "identically": [41], "distributed": [42], "(non-IID)": [43], "incurs": [46], "high": [47], "communication": [48], "costs.": [49], "To": [50], "address": [51], "these": [52], "challenges,": [53], "we": [54], "propose": [55], "framework": [59, 89], "that": [60, 158], "integrates": [61], "frozen": [63], "Contrastive": [64], "Language-Image": [65], "Pre-training": [66], "(CLIP)": [67], "vision": [68], "transformer": [69, 74], "(ViT)": [70], "lightweight": [73], "classifier.": [75], "By": [76], "leveraging": [77], "the": [78, 84, 88, 159, 180], "strong": [79], "feature": [80, 125], "extraction": [81], "capability": [82], "of": [83, 123, 184], "pre-trained": [85], "CLIP": [86], "ViT,": [87], "avoids": [90], "models": [93], "from": [94, 127], "scratch": [95], "restricts": [97], "updates": [99], "to": [100, 110, 139, 173], "compact": [102], "classifier,": [103], "thereby": [104], "reducing": [105], "transmission": [106], "overhead": [107], "significantly.": [108], "Furthermore,": [109], "mitigate": [111], "performance": [112], "degradation": [113], "caused": [114], "by": [115], "non-IID": [116], "distribution,": [118], "small": [120], "subset": [121], "(1%)": [122], "CLIP-extracted": [124], "representations": [126], "all": [128], "classes": [129], "is": [130, 166], "shared": [131, 135], "across": [132, 149], "clients.": [133], "These": [134], "features": [136, 188], "are": [137], "non-reversible": [138], "raw": [140], "images,": [141], "ensuring": [142], "preservation": [144], "aligning": [146], "class": [147], "representation": [148], "participants.": [150], "Experimental": [151], "results": [152], "on": [153], "agricultural": [154, 196], "tasks": [156], "show": [157], "proposed": [160], "method": [161], "achieve": [162], "86.6%": [163], "accuracy,": [164], "more": [167], "than": [168], "4": [169], "times": [170], "higher": [171], "compared": [172], "baseline": [174], "approaches.": [177], "This": [178], "demonstrates": [179], "effectiveness": [181], "efficiency": [183], "combining": [185], "vision-language": [186], "model": [187], "for": [192], "privacy-preserving": [193], "scalable": [195], "intelligence.": [197]}, "primary_topic": {"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9775000214576721, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9775000214576721, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10616", "display_name": "Smart Agriculture and AI", "score": 0.01730000041425228, "subfield": {"id": "https://openalex.org/subfields/1110", "display_name": "Plant Science"}, "field": {"id": "https://openalex.org/fields/11", "display_name": "Agricultural and Biological Sciences"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.0034000000450760126, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.00269", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.00269", "pdf_url": "https://arxiv.org/pdf/2511.00269", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416933884", "doi": "https://doi.org/10.12701/jyms.2025.42.79", "title": "Why large language models cannot possess consciousness: an integrated information theory perspective", "publication_year": 2025, "publication_date": "2025-12-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5070764607", "display_name": "Dong Ah Shin", "orcid": "https://orcid.org/0000-0002-5225-4083", "observed_orcids": ["https://orcid.org/0000-0002-5225-4083"]}, "institutions": [{"id": "https://openalex.org/I193775966", "display_name": "Yonsei University", "ror": "https://ror.org/01wjejq96", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I193775966"]}, {"id": "https://openalex.org/I2799970807", "display_name": "Severance Hospital", "ror": "https://ror.org/044kjp413", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807", "https://openalex.org/I4210160791"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Dong Ah Shin", "raw_affiliation_strings": ["Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea"], "raw_orcid": "https://orcid.org/0000-0002-5225-4083", "affiliations": [{"raw_affiliation_string": "Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea", "institution_ids": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082926383", "display_name": "Pyung Goo Cho", "orcid": "https://orcid.org/0000-0001-7087-8597", "observed_orcids": ["https://orcid.org/0000-0001-7087-8597"]}, "institutions": [{"id": "https://openalex.org/I4210103252", "display_name": "Ajou University Hospital", "ror": "https://ror.org/01bzpky79", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I4210103252", "https://openalex.org/I57664883"]}, {"id": "https://openalex.org/I57664883", "display_name": "Ajou University", "ror": "https://ror.org/03tzb2h73", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I57664883"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Pyung Goo Cho", "raw_affiliation_strings": ["Department of Neurosurgery, Ajou University Hospital, Ajou University School of Medicine, Suwon, Korea"], "raw_orcid": "https://orcid.org/0000-0001-7087-8597", "affiliations": [{"raw_affiliation_string": "Department of Neurosurgery, Ajou University Hospital, Ajou University School of Medicine, Suwon, Korea", "institution_ids": ["https://openalex.org/I4210103252", "https://openalex.org/I57664883"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5069163525", "display_name": "Gyu Yeul Ji", "orcid": "https://orcid.org/0000-0002-8818-5091", "observed_orcids": ["https://orcid.org/0000-0002-8818-5091"]}, "institutions": [{"id": "https://openalex.org/I193775966", "display_name": "Yonsei University", "ror": "https://ror.org/01wjejq96", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I193775966"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Gyu Yeul Ji", "raw_affiliation_strings": ["Department of Neurosurgery, Yonsei Hana Hospital, Gimpo, Korea"], "raw_orcid": "https://orcid.org/0000-0002-8818-5091", "affiliations": [{"raw_affiliation_string": "Department of Neurosurgery, Yonsei Hana Hospital, Gimpo, Korea", "institution_ids": ["https://openalex.org/I193775966"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Sang Hyuk Park", "orcid": "https://orcid.org/0009-0003-0235-0581", "observed_orcids": ["https://orcid.org/0009-0003-0235-0581"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sang Hyuk Park", "raw_affiliation_strings": ["Yonsei Good Walk Clinic, Anyang, Korea"], "raw_orcid": "https://orcid.org/0009-0003-0235-0581", "affiliations": [{"raw_affiliation_string": "Yonsei Good Walk Clinic, Anyang, Korea", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Soo Heon Kim", "orcid": "https://orcid.org/0009-0000-9332-7181", "observed_orcids": ["https://orcid.org/0009-0000-9332-7181"]}, "institutions": [{"id": "https://openalex.org/I193775966", "display_name": "Yonsei University", "ror": "https://ror.org/01wjejq96", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I193775966"]}, {"id": "https://openalex.org/I2799970807", "display_name": "Severance Hospital", "ror": "https://ror.org/044kjp413", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807", "https://openalex.org/I4210160791"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Soo Heon Kim", "raw_affiliation_strings": ["Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea"], "raw_orcid": "https://orcid.org/0009-0000-9332-7181", "affiliations": [{"raw_affiliation_string": "Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea", "institution_ids": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5001078576", "display_name": "Yoo Jin Choo", "orcid": "https://orcid.org/0000-0002-3820-2279", "observed_orcids": ["https://orcid.org/0000-0002-3820-2279"]}, "institutions": [{"id": "https://openalex.org/I4210149656", "display_name": "Yeungnam University Medical Center", "ror": "https://ror.org/04ntyjt11", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I4210149656", "https://openalex.org/I55240360"]}, {"id": "https://openalex.org/I4400573303", "display_name": "Yeungnam University College", "ror": "https://ror.org/05e6g0130", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4400573303"]}, {"id": "https://openalex.org/I55240360", "display_name": "Yeungnam University", "ror": "https://ror.org/05yc6p159", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I55240360"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Yoo Jin Choo", "raw_affiliation_strings": ["Department of Physical Medicine and Rehabilitation, Yeungnam University College of Medicine, Daegu, Korea"], "raw_orcid": "https://orcid.org/0000-0002-3820-2279", "affiliations": [{"raw_affiliation_string": "Department of Physical Medicine and Rehabilitation, Yeungnam University College of Medicine, Daegu, Korea", "institution_ids": ["https://openalex.org/I4210149656", "https://openalex.org/I4400573303", "https://openalex.org/I55240360"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100665228", "display_name": "Min Cheol Chang", "orcid": "https://orcid.org/0000-0002-7629-7213", "observed_orcids": ["https://orcid.org/0000-0002-7629-7213"]}, "institutions": [{"id": "https://openalex.org/I193775966", "display_name": "Yonsei University", "ror": "https://ror.org/01wjejq96", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I193775966"]}, {"id": "https://openalex.org/I2799970807", "display_name": "Severance Hospital", "ror": "https://ror.org/044kjp413", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807", "https://openalex.org/I4210160791"]}, {"id": "https://openalex.org/I4210103252", "display_name": "Ajou University Hospital", "ror": "https://ror.org/01bzpky79", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I4210103252", "https://openalex.org/I57664883"]}, {"id": "https://openalex.org/I4210149656", "display_name": "Yeungnam University Medical Center", "ror": "https://ror.org/04ntyjt11", "country_code": "KR", "type": "healthcare", "lineage": ["https://openalex.org/I4210149656", "https://openalex.org/I55240360"]}, {"id": "https://openalex.org/I4400573303", "display_name": "Yeungnam University College", "ror": "https://ror.org/05e6g0130", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4400573303"]}, {"id": "https://openalex.org/I55240360", "display_name": "Yeungnam University", "ror": "https://ror.org/05yc6p159", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I55240360"]}, {"id": "https://openalex.org/I57664883", "display_name": "Ajou University", "ror": "https://ror.org/03tzb2h73", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I57664883"]}], "countries": ["KR"], "is_corresponding": true, "raw_author_name": "Min Cheol Chang", "raw_affiliation_strings": ["Department of Physical Medicine and Rehabilitation, Yeungnam University College of Medicine, Daegu, Korea", "Department of Neurosurgery, Ajou University Hospital, Ajou University School of Medicine, Suwon, Korea", "Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea", "Yonsei Good Walk Clinic, Anyang, Korea"], "raw_orcid": "https://orcid.org/0000-0002-7629-7213", "affiliations": [{"raw_affiliation_string": "Department of Physical Medicine and Rehabilitation, Yeungnam University College of Medicine, Daegu, Korea", "institution_ids": ["https://openalex.org/I4210149656", "https://openalex.org/I4400573303", "https://openalex.org/I55240360"]}, {"raw_affiliation_string": "Department of Neurosurgery, Ajou University Hospital, Ajou University School of Medicine, Suwon, Korea", "institution_ids": ["https://openalex.org/I4210103252", "https://openalex.org/I57664883"]}, {"raw_affiliation_string": "Department of Neurosurgery, Spine and Spinal Cord Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea", "institution_ids": ["https://openalex.org/I193775966", "https://openalex.org/I2799970807"]}, {"raw_affiliation_string": "Yonsei Good Walk Clinic, Anyang, Korea", "institution_ids": []}]}], "abstract_inverted_index": {"BACKGROUND:": [0], "The": [1, 89], "question": [2], "of": [3, 29, 41, 85, 92, 107, 145, 153, 194, 215, 221, 233], "whether": [4], "large": [5], "language": [6], "models": [7], "(LLMs)": [8], "possess": [9], "consciousness": [10, 25, 216], "has": [11], "been": [12], "increasingly": [13], "debated.": [14], "Integrated": [15], "information": [16, 79], "theory": [17], "(IIT)": [18], "offers": [19], "a": [20, 27, 74, 93, 119, 128, 230], "quantitative": [21], "framework": [22], "for": [23, 77], "assessing": [24], "through": [26], "measure": [28, 84], "integrated": [30, 78, 86, 234], "information.": [31, 87], "METHODS:": [32], "This": [33], "study": [34, 91], "applied": [35], "IIT": [36, 143], "principles": [37], "to": [38, 80, 149], "the": [39, 83, 142, 151, 188, 191, 210, 237], "architecture": [40], "transformer-based": [42], "LLMs,": [43], "focusing": [44], "on": [45, 55], "causal": [46, 155, 177], "integration,": [47, 154], "temporal": [48, 158], "persistence,": [49], "and": [50, 68, 157, 172, 212, 242], "system": [51], "irreducibility.": [52, 178], "Ablation": [53], "experiments": [54], "Generative": [56], "Pretrained": [57], "Transformer": [58], "2": [59], "(GPT-2)": [60], "were": [61], "performed,": [62], "selectively": [63], "removing": [64], "individual": [65], "attention": [66, 95], "heads": [67], "measuring": [69], "changes": [70, 101], "in": [71, 102, 104, 122], "perplexity": [72, 103, 123], "as": [73], "behavioral": [75], "proxy": [76], "empirically": [81], "approximate": [82], "RESULTS:": [88], "ablation": [90], "single": [94], "head": [96], "produced": [97], "minimal": [98], "or": [99, 113], "negative": [100], "four": [105], "out": [106], "five": [108], "representative": [109], "sentences,": [110], "indicating": [111], "redundancy": [112], "noise.": [114], "Only": [115], "one": [116], "sentence": [117], "revealed": [118], "significant": [120], "increase": [121], "change": [124], "(\u0394PPL": [125], "+11.29),": [126], "reflecting": [127], "localized": [129], "but": [130, 147], "nonessential": [131], "contribution.": [132], "A": [133], "comparison": [134], "with": [135, 229], "biological": [136], "systems": [137, 228], "demonstrated": [138], "that": [139, 163, 190], "LLMs": [140, 164, 195, 206, 225], "meet": [141, 150], "criterion": [144], "differentiation,": [146], "fail": [148], "criteria": [152], "closure,": [156], "persistence.": [159], "These": [160], "findings": [161], "confirm": [162], "are": [165], "architecturally": [166], "decomposable,": [167], "lack": [168], "persistent": [169], "internal": [170], "states,": [171], "do": [173, 207], "not": [174, 208], "sustain": [175], "global": [176], "Philosophical": [179], "considerations,": [180], "including": [181], "Searle's": [182], "Chinese": [183], "Room": [184], "argument,": [185], "further": [186], "support": [187], "idea": [189], "linguistic": [192, 240], "fluency": [193], "arises": [196], "from": [197], "syntactic": [198], "manipulation": [199], "rather": [200], "than": [201], "semantic": [202], "understanding.": [203], "CONCLUSION:": [204], "Current": [205], "satisfy": [209], "structural": [211], "informational": [213], "requirements": [214], "under": [217], "IIT.": [218], "Although": [219], "capable": [220], "simulating": [222], "intelligent": [223], "language,": [224], "remain": [226], "unconscious": [227], "negligible": [231], "amount": [232], "information,": [235], "underscoring": [236], "distinction": [238], "between": [239], "competence": [241], "conscious": [243], "experience.": [244]}, "primary_topic": {"id": "https://openalex.org/T10258", "display_name": "Philosophy and Theoretical Science", "score": 0.9765999913215637, "subfield": {"id": "https://openalex.org/subfields/3205", "display_name": "Experimental and Cognitive Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, "topics": [{"id": "https://openalex.org/T10258", "display_name": "Philosophy and Theoretical Science", "score": 0.9765999913215637, "subfield": {"id": "https://openalex.org/subfields/3205", "display_name": "Experimental and Cognitive Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}, {"id": "https://openalex.org/T14381", "display_name": "Psychiatry, Mental Health, Neuroscience", "score": 0.0044999998062849045, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13308", "display_name": "Cybernetics and Technology in Society", "score": 0.0034000000450760126, "subfield": {"id": "https://openalex.org/subfields/1207", "display_name": "History and Philosophy of Science"}, "field": {"id": "https://openalex.org/fields/12", "display_name": "Arts and Humanities"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.12701/jyms.2025.42.79", "is_oa": true, "landing_page_url": "https://doi.org/10.12701/jyms.2025.42.79", "pdf_url": "https://www.e-jyms.org/upload/pdf/jyms-2025-42-79.pdf", "source": {"id": "https://openalex.org/S4210230485", "display_name": "Journal of Yeungnam Medical Science", "issn_l": "1225-7737", "issn": ["1225-7737", "2234-8042", "2384-0293", "2799-8010"], "is_oa": true, "is_in_doaj": true, "is_core": false, "listed_in": ["doaj"], "host_organization": "https://openalex.org/P4362643773", "host_organization_name": "Yeungnam University College of Medicine", "host_organization_lineage": ["https://openalex.org/P4362643773"], "host_organization_lineage_names": ["Yeungnam University College of Medicine"], "type": "journal"}, "license": "cc-by-nc", "license_id": "https://openalex.org/licenses/cc-by-nc", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Yeungnam Medical Science", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4408787042", "doi": "https://doi.org/10.2196/preprints.74142", "title": "Evaluating Reasoning Capabilities of Large Language Models for Medical Coding and Hospital Readmission Risk Stratification with Zero Shot Prompting (Preprint)", "publication_year": 2025, "publication_date": "2025-03-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5015986084", "display_name": "Parvati Naliyatthaliyazchayil", "orcid": "https://orcid.org/0009-0003-5917-4558", "observed_orcids": ["https://orcid.org/0009-0003-5917-4558"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Parvati Naliyatthaliyazchayil", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0003-5917-4558", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5116651915", "display_name": "Raajitha Muthyala", "orcid": "https://orcid.org/0009-0000-6196-3116", "observed_orcids": ["https://orcid.org/0009-0000-6196-3116"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Raajitha Muthyala", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076075666", "display_name": "Judy Wawira Gichoya", "orcid": "https://orcid.org/0000-0002-1097-316X", "observed_orcids": ["https://orcid.org/0000-0002-1097-316X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Judy Wawira Gichoya", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0002-1097-316X", "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5075722115", "display_name": "Saptarshi Purkayastha", "orcid": "https://orcid.org/0000-0003-3625-534X", "observed_orcids": ["https://orcid.org/0000-0003-3625-534X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Saptarshi Purkayastha", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0003-3625-534X", "affiliations": []}], "abstract_inverted_index": {"BACKGROUND": [0], "The": [1, 149], "proliferation": [2], "of": [3, 38, 59, 91, 154, 305, 326, 345], "large": [4], "language": [5], "models": [6, 20, 203, 268, 308, 347], "(LLMs)": [7], "through": [8, 145], "accessible": [9], "chatbot": [10], "interfaces": [11], "has": [12], "created": [13], "unprecedented": [14], "opportunities": [15], "in": [16, 40, 81, 184, 251, 256, 262, 281, 294], "healthcare,": [17], "with": [18, 55, 161, 248, 275, 315, 324, 335], "state-of-the-art": [19], "such": [21], "as": [22], "ChatGPT-4,": [23, 98], "LLaMA-3\u00b71,": [24, 99], "Gemini-1\u00b75,": [25, 100], "DeepSeek-R1and": [26, 101], "OpenAI-O3,": [27], "offering": [28], "artificial": [29], "intelligence-driven": [30], "clinical": [31, 60, 178, 310, 351], "support.": [32], "Some": [33], "studies": [34], "showcase": [35], "the": [36, 56, 111, 124, 199, 221, 227, 306, 319, 327, 340], "potential": [37, 71], "LLMs": [39, 96, 333], "managing": [41], "complex": [42], "healthcare": [43, 108], "tasks,": [44, 314], "while": [45, 289], "others": [46], "emphasize": [47], "concerns": [48], "regarding": [49], "their": [50, 69, 206, 350], "accuracy,": [51], "reliability,": [52], "and": [53, 72, 94, 138, 180, 211, 260, 270, 285], "compliance": [54], "rigorous": [57], "standards": [58, 311], "settings.": [61], "This": [62, 84, 322, 338], "study": [63, 85, 150], "was": [64, 172], "conducted": [65], "to": [66, 135, 174, 204, 348], "better": [67, 293], "understand": [68], "true": [70], "identify": [73], "areas": [74], "where": [75], "they": [76], "can": [77], "be": [78], "most": [79], "effective": [80], "healthcare.": [82], "OBJECTIVE": [83], "presents": [86], "a": [87, 152, 185, 217], "comprehensive": [88], "comparative": [89, 234], "analysis": [90, 235], "leading": [92], "reasoning": [93, 207], "non-reasoning": [95, 237], "-": [97, 103], "OpenAI-O3": [102, 271], "evaluated": [104, 307], "across": [105, 244, 312], "three": [106], "critical": [107], "tasks": [109], "using": [110], "Medical": [112], "Information": [113], "Mart": [114], "for": [115, 209, 342], "Intensive": [116], "Care": [117], "IV": [118], "(MIMIC-IV)": [119], "dataset.": [120], "METHODS": [121], "We": [122], "assessed": [123], "model": [125], "capabilities": [126], "in:": [127], "(1)": [128], "generating": [129], "primary": [130, 282], "diagnoses,": [131], "(2)": [132], "mapping": [133], "diagnoses": [134], "ICD-9": [136, 257, 286], "codes,": [137], "(3)": [139], "predicting": [140], "hospital": [141, 263], "readmission": [142, 264, 295], "risk": [143, 265, 296], "stratification": [144], "zero-shot": [146, 218], "prompting": [147, 200], "protocols.": [148], "utilized": [151], "cohort": [153], "300": [155], "randomly": [156], "selected": [157], "subjects": [158], "from": [159, 166], "MIMIC-IV,": [160], "standardized": [162], "prompts": [163], "systematically": [164], "generated": [165], "discharge": [167], "summary": [168], "sections.": [169], "Each": [170], "prompt": [171, 219, 222], "engineered": [173], "incorporate": [175], "both": [176], "patient": [177], "information": [179], "specific": [181], "task": [182], "requirements": [183], "unified": [186], "input": [187], "format.": [188], "To": [189], "enhance": [190, 349], "result": [191], "interpretability,": [192], "we": [193], "implemented": [194], "explicit": [195], "rationale": [196], "elicitation": [197], "within": [198], "structure,": [201], "requiring": [202], "articulate": [205], "process": [208], "diagnostic": [210], "prognostic": [212], "predictions.": [213], "Since": [214], "this": [215], "is": [216, 223], "approach,": [220], "not": [224], "tested,": [225], "repeating": [226], "same": [228], "multiple": [229], "times.": [230], "RESULTS": [231], "In": [232], "our": [233], "among": [236], "models,": [238], "LLaMA-3\u00b71": [239], "demonstrated": [240], "superior": [241], "aggregate": [242], "performance": [243], "all": [245, 313], "evaluation": [246], "metrics,": [247], "85%": [249], "correctness": [250], "Primary": [252], "Diagnosis": [253], "prediction,": [254, 259], "42\u00b76%": [255], "code": [258], "41\u00b73%": [261], "prediction.": [266], "Reasoning": [267], "DeepSeek-R1": [269], "showed": [272], "similar": [273], "performance,": [274], "O3": [276], "achieving": [277], "slightly": [278, 292], "higher": [279], "accuracy": [280], "diagnosis": [283], "(90%)": [284], "prediction": [287, 297], "(45\u00b73%),": [288], "R1": [290], "performed": [291], "(72\u00b766%).": [298], "CONCLUSIONS": [299], "Our": [300], "findings": [301, 329], "show": [302], "that": [303, 331], "none": [304], "met": [309], "medical": [316, 336], "coding": [317], "showing": [318], "weakest": [320], "performance.": [321], "aligns": [323], "few": [325], "literature": [328], "indicating": [330], "pretrained": [332], "struggle": [334], "coding.": [337], "underscores": [339], "need": [341], "further": [343], "refinement": [344], "these": [346], "applicability.": [352]}, "primary_topic": {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.6791999936103821, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.6791999936103821, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.31200000643730164, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11396", "display_name": "Artificial Intelligence in Healthcare", "score": 0.00419999985024333, "subfield": {"id": "https://openalex.org/subfields/3605", "display_name": "Health Information Management"}, "field": {"id": "https://openalex.org/fields/36", "display_name": "Health Professions"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.2196/preprints.74142", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/preprints.74142", "pdf_url": null, "source": null, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7116722309", "doi": "https://doi.org/10.1177/17248035251345711", "title": "An Iterative Multi-aspect term Extraction and Polarity Detection Approach Based on spanBERT for Aspect-based Sentiment Analysis", "publication_year": 2025, "publication_date": "2025-05-29", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5038519736", "display_name": "Abubakar Muhammad Ashir", "orcid": "https://orcid.org/0000-0003-4009-8463", "observed_orcids": ["https://orcid.org/0000-0003-4009-8463"]}, "institutions": [{"id": "https://openalex.org/I908820301", "display_name": "Tishk International University", "ror": "https://ror.org/03pbhyy22", "country_code": "IQ", "type": "education", "lineage": ["https://openalex.org/I908820301"]}], "countries": ["IQ"], "is_corresponding": true, "raw_author_name": "Abubakar M Ashir", "raw_affiliation_strings": ["Computer Engineering Department, Tishk International University, Erbil, Iraq"], "raw_orcid": "https://orcid.org/0000-0003-4009-8463", "affiliations": [{"raw_affiliation_string": "Computer Engineering Department, Tishk International University, Erbil, Iraq", "institution_ids": ["https://openalex.org/I908820301"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5012304725", "display_name": "Mohammed Abdulghani Taha", "orcid": "https://orcid.org/0000-0003-1832-1358", "observed_orcids": ["https://orcid.org/0000-0003-1832-1358"]}, "institutions": [{"id": "https://openalex.org/I908820301", "display_name": "Tishk International University", "ror": "https://ror.org/03pbhyy22", "country_code": "IQ", "type": "education", "lineage": ["https://openalex.org/I908820301"]}], "countries": ["IQ"], "is_corresponding": false, "raw_author_name": "Mohammed Abdulghani Taha", "raw_affiliation_strings": ["Computer Engineering Department, Tishk International University, Erbil, Iraq"], "raw_orcid": "https://orcid.org/0000-0003-1832-1358", "affiliations": [{"raw_affiliation_string": "Computer Engineering Department, Tishk International University, Erbil, Iraq", "institution_ids": ["https://openalex.org/I908820301"]}]}], "abstract_inverted_index": {"Aspect-based": [0], "sentiment": [1, 68, 79, 181], "analysis": [2, 7, 69, 80], "(ABSA)": [3], "is": [4, 38], "a": [5, 23, 28, 97, 141, 211, 218, 262], "fine-grained": [6], "of": [8, 36, 46, 94, 110, 129, 133, 164, 215, 233, 271, 277, 295], "sentiments": [9], "and": [10, 42, 49, 77, 136, 184, 222, 269], "opinions": [11], "expressed": [12], "in": [13, 51, 140, 149, 210], "text": [14, 197, 216], "document": [15, 24], "which": [16, 116], "set": [17], "aside": [18], "the": [19, 44, 57, 91, 111, 126, 160, 176, 226, 230, 234, 242, 248, 258, 267, 272, 275, 286, 296], "na\u00efve": [20], "assumption": [21], "that": [22], "expresses": [25], "opinion": [26], "about": [27], "single": [29, 98], "topic": [30], "or": [31], "aspect.": [32], "The": [33, 123, 153, 203, 239, 252], "main": [34], "objective": [35], "ABSA": [37, 60, 95, 301], "to": [39, 89, 125, 144, 172, 194, 244, 280], "spot,": [40], "extract": [41], "identify": [43], "polarity": [45, 182], "different": [47], "entities": [48], "aspects": [50], "an": [52, 85, 199], "opinionated": [53], "document.": [54], "Based": [55], "on": [56, 96, 108, 159], "previous": [58], "works,": [59], "can": [61], "be": [62, 281], "categorized": [63], "into": [64, 229], "three": [65, 92], "subtasks:": [66], "Aspect-category": [67], "(ACSA),": [70], "Opinion": [71], "Target": [72], "Expression": [73], "Sentiment": [74], "Analysis": [75], "(OTESA)": [76], "Aspect-term": [78], "(ATSA).": [81], "This": [82], "research": [83, 298], "presents": [84], "end-to-end": [86], "multi-task": [87], "approach": [88, 190, 287], "performing": [90], "categories": [93], "pipeline.": [99], "A": [100, 187], "ternary": [101, 154], "multitask": [102], "learning": [103], "objectives": [104], "classifiers": [105, 260], "were": [106, 157, 291], "built": [107, 158], "top": [109], "baseline": [112], "spanBERT": [113, 166], "language": [114, 151], "model": [115, 127, 235], "was": [117, 191], "originally": [118], "pretrained": [119, 165], "for": [120, 236, 247], "span": [121, 178, 188, 204, 214, 250, 254, 259, 273, 279], "extraction.": [122], "input": [124, 232], "consists": [128], "two": [130], "merged": [131], "segments": [132], "entity": [134], "premises": [135], "context": [137, 174], "data": [138], "hypothesis": [139], "similar": [142], "passion": [143], "reading": [145], "comprehension": [146], "downstream": [147, 155], "task": [148], "natural": [150], "processing.": [152], "tasks": [156], "contextualized": [161], "output": [162], "embeddings": [163], "entangled": [167], "with": [168, 175, 217, 299], "cross-layer": [169], "attention": [170], "mechanism": [171], "associate": [173], "aspect-term": [177], "extraction,": [179], "aspect": [180], "detection": [183], "entity-aspect": [185], "entailment.": [186], "masking": [189, 205, 255], "also": [192], "proposed": [193], "address": [195], "multiple-aspects": [196], "using": [198], "iterative": [200], "outputs-inputs": [201], "loopback.": [202], "process": [206], "replaces": [207], "each": [208], "word": [209], "previously": [212], "detected": [213], "special": [219, 263], "[MASK]": [220], "character": [221], "then": [223], "feeds": [224], "back": [225], "entire": [227], "sentence": [228], "encoder": [231, 243], "next": [237, 249], "run.": [238], "technique": [240], "forces": [241], "look": [245], "elsewhere": [246], "prediction.": [251], "loopback": [253], "terminates": [256], "when": [257], "predict": [261], "token": [264], "[CLS]": [265], "as": [266, 288], "beginning": [268], "end": [270], "signaling": [274], "absent": [276], "relatable": [278], "extracted.": [282], "Experimental": [283], "results": [284, 290], "validate": [285], "impressive": [289], "obtained": [292], "outperforming": [293], "most": [294], "compared": [297], "benchmark": [300], "datasets.": [302]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T12262", "display_name": "Hate Speech and Cyberbullying Detection", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1177/17248035251345711", "is_oa": false, "landing_page_url": "https://doi.org/10.1177/17248035251345711", "pdf_url": null, "source": {"id": "https://openalex.org/S207922018", "display_name": "Intelligenza Artificiale", "issn_l": "1724-8035", "issn": ["1724-8035", "2211-0097"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core"], "host_organization": "https://openalex.org/P4310318577", "host_organization_name": "IOS Press", "host_organization_lineage": ["https://openalex.org/P4310318577"], "host_organization_lineage_names": ["IOS Press"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Intelligenza Artificiale", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411141175", "doi": "https://doi.org/10.1200/cci-25-00071", "title": "Enhancing Patient-Trial Matching With Large Language Models: A Scoping Review of Emerging Applications and Approaches", "publication_year": 2025, "publication_date": "2025-06-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5058239840", "display_name": "Hongyu Chen", "orcid": "https://orcid.org/0000-0001-6259-0833", "observed_orcids": ["https://orcid.org/0000-0001-6259-0833"]}, "institutions": [{"id": "https://openalex.org/I2800717037", "display_name": "University of Florida Health", "ror": "https://ror.org/04tk2gy88", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I2800717037"]}, {"id": "https://openalex.org/I33213144", "display_name": "University of Florida", "ror": "https://ror.org/02y3ad647", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I33213144"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Hongyu Chen", "raw_affiliation_strings": ["Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL"], "raw_orcid": "https://orcid.org/0000-0001-6259-0833", "affiliations": [{"raw_affiliation_string": "Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL", "institution_ids": ["https://openalex.org/I2800717037", "https://openalex.org/I33213144"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Xiaohan Li", "orcid": "https://orcid.org/0009-0004-6679-5560", "observed_orcids": ["https://orcid.org/0009-0004-6679-5560"]}, "institutions": [{"id": "https://openalex.org/I2800717037", "display_name": "University of Florida Health", "ror": "https://ror.org/04tk2gy88", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I2800717037"]}, {"id": "https://openalex.org/I33213144", "display_name": "University of Florida", "ror": "https://ror.org/02y3ad647", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I33213144"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xiaohan Li", "raw_affiliation_strings": ["Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL"], "raw_orcid": "https://orcid.org/0009-0004-6679-5560", "affiliations": [{"raw_affiliation_string": "Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL", "institution_ids": ["https://openalex.org/I2800717037", "https://openalex.org/I33213144"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079221585", "display_name": "Xing He", "orcid": "https://orcid.org/0000-0003-0290-8058", "observed_orcids": ["https://orcid.org/0000-0003-0290-8058", "https://orcid.org/0009-0005-4841-2316"]}, "institutions": [{"id": "https://openalex.org/I1324682000", "display_name": "Regenstrief Institute", "ror": "https://ror.org/05f2ywb48", "country_code": "US", "type": "nonprofit", "lineage": ["https://openalex.org/I1324682000"]}, {"id": "https://openalex.org/I4388446366", "display_name": "Indiana University Indianapolis", "ror": "https://ror.org/03eftgw80", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I4394709130", "display_name": "Indiana University School of Medicine", "ror": "https://ror.org/02ets8c94", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4394709130", "https://openalex.org/I592451"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xing He", "raw_affiliation_strings": ["Department of Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN", "Regenstrief Institute, Indianapolis, IN"], "raw_orcid": "https://orcid.org/0000-0003-0290-8058", "affiliations": [{"raw_affiliation_string": "Department of Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN", "institution_ids": ["https://openalex.org/I4388446366", "https://openalex.org/I4394709130"]}, {"raw_affiliation_string": "Regenstrief Institute, Indianapolis, IN", "institution_ids": ["https://openalex.org/I1324682000"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5004483523", "display_name": "Aokun Chen", "orcid": "https://orcid.org/0000-0002-5100-3821", "observed_orcids": ["https://orcid.org/0000-0002-5100-3821"]}, "institutions": [{"id": "https://openalex.org/I2800717037", "display_name": "University of Florida Health", "ror": "https://ror.org/04tk2gy88", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I2800717037"]}, {"id": "https://openalex.org/I33213144", "display_name": "University of Florida", "ror": "https://ror.org/02y3ad647", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I33213144"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Aokun Chen", "raw_affiliation_strings": ["Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL"], "raw_orcid": "https://orcid.org/0000-0002-5100-3821", "affiliations": [{"raw_affiliation_string": "Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL", "institution_ids": ["https://openalex.org/I2800717037", "https://openalex.org/I33213144"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109577464", "display_name": "James M. McGill", "orcid": "https://orcid.org/0000-0003-0588-5680", "observed_orcids": ["https://orcid.org/0000-0003-0588-5680"]}, "institutions": [{"id": "https://openalex.org/I1283055418", "display_name": "Indiana University Health", "ror": "https://ror.org/01aaptx40", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283055418", "https://openalex.org/I4388446366", "https://openalex.org/I592451"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "James McGill", "raw_affiliation_strings": ["Indiana University Health, Indianapolis, IN"], "raw_orcid": "https://orcid.org/0000-0003-0588-5680", "affiliations": [{"raw_affiliation_string": "Indiana University Health, Indianapolis, IN", "institution_ids": ["https://openalex.org/I1283055418"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5002140899", "display_name": "Emily Chui Webber", "orcid": "https://orcid.org/0000-0001-5877-6707", "observed_orcids": ["https://orcid.org/0000-0001-5877-6707"]}, "institutions": [{"id": "https://openalex.org/I1283055418", "display_name": "Indiana University Health", "ror": "https://ror.org/01aaptx40", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283055418", "https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I255400825", "display_name": "Indiana University Hospital", "ror": "https://ror.org/05rbkcx47", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283055418", "https://openalex.org/I255400825", "https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I2802740592", "display_name": "Riley Hospital for Children", "ror": "https://ror.org/03vzvbw58", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I1283055418", "https://openalex.org/I2802740592", "https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I4388446366", "display_name": "Indiana University Indianapolis", "ror": "https://ror.org/03eftgw80", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I4394709130", "display_name": "Indiana University School of Medicine", "ror": "https://ror.org/02ets8c94", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4394709130", "https://openalex.org/I592451"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Emily C. Webber", "raw_affiliation_strings": ["Division of Pediatric Hospital Medicine, School of Medicine, Indiana University, Indianapolis, IN", "Riley Hospital for Children at Indiana University Health, Indianapolis, IN"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Division of Pediatric Hospital Medicine, School of Medicine, Indiana University, Indianapolis, IN", "institution_ids": ["https://openalex.org/I255400825", "https://openalex.org/I4388446366", "https://openalex.org/I4394709130"]}, {"raw_affiliation_string": "Riley Hospital for Children at Indiana University Health, Indianapolis, IN", "institution_ids": ["https://openalex.org/I1283055418", "https://openalex.org/I2802740592"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5084072550", "display_name": "Hua Xu", "orcid": "https://orcid.org/0000-0002-5274-4672", "observed_orcids": ["https://orcid.org/0000-0002-5274-4672"]}, "institutions": [{"id": "https://openalex.org/I32971472", "display_name": "Yale University", "ror": "https://ror.org/03v76x132", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I32971472"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Hua Xu", "raw_affiliation_strings": ["Section of Biomedical Informatics and Data Science, School of Medicine, Yale University, Yale, NH"], "raw_orcid": "https://orcid.org/0000-0002-5274-4672", "affiliations": [{"raw_affiliation_string": "Section of Biomedical Informatics and Data Science, School of Medicine, Yale University, Yale, NH", "institution_ids": ["https://openalex.org/I32971472"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5036466755", "display_name": "Mei Liu", "orcid": "https://orcid.org/0000-0002-8036-2110", "observed_orcids": ["https://orcid.org/0000-0002-8036-2110"]}, "institutions": [{"id": "https://openalex.org/I2800717037", "display_name": "University of Florida Health", "ror": "https://ror.org/04tk2gy88", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I2800717037"]}, {"id": "https://openalex.org/I33213144", "display_name": "University of Florida", "ror": "https://ror.org/02y3ad647", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I33213144"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Mei Liu", "raw_affiliation_strings": ["Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL"], "raw_orcid": "https://orcid.org/0000-0002-8036-2110", "affiliations": [{"raw_affiliation_string": "Department of Health Outcomes &amp; Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL", "institution_ids": ["https://openalex.org/I2800717037", "https://openalex.org/I33213144"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030951014", "display_name": "Jiang Bian", "orcid": "https://orcid.org/0000-0002-2238-5429", "observed_orcids": ["https://orcid.org/0000-0002-2238-5429"]}, "institutions": [{"id": "https://openalex.org/I1324682000", "display_name": "Regenstrief Institute", "ror": "https://ror.org/05f2ywb48", "country_code": "US", "type": "nonprofit", "lineage": ["https://openalex.org/I1324682000"]}, {"id": "https://openalex.org/I4388446366", "display_name": "Indiana University Indianapolis", "ror": "https://ror.org/03eftgw80", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I4388446366", "https://openalex.org/I592451"]}, {"id": "https://openalex.org/I4394709130", "display_name": "Indiana University School of Medicine", "ror": "https://ror.org/02ets8c94", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4394709130", "https://openalex.org/I592451"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Jiang Bian", "raw_affiliation_strings": ["Department of Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN", "Regenstrief Institute, Indianapolis, IN"], "raw_orcid": "https://orcid.org/0000-0002-2238-5429", "affiliations": [{"raw_affiliation_string": "Department of Biostatistics and Health Data Science, School of Medicine, Indiana University, Indianapolis, IN", "institution_ids": ["https://openalex.org/I4388446366", "https://openalex.org/I4394709130"]}, {"raw_affiliation_string": "Regenstrief Institute, Indianapolis, IN", "institution_ids": ["https://openalex.org/I1324682000"]}]}], "abstract_inverted_index": {"PURPOSE:": [0], "Patient": [1], "recruitment": [2, 268], "remains": [3], "a": [4, 28, 43, 209], "major": [5], "bottleneck": [6], "in": [7, 22, 52, 61, 126, 134, 185, 235, 265], "clinical": [8, 219, 271], "trial": [9, 220, 250, 272], "execution,": [10], "with": [11, 143, 169], "inefficient": [12], "patient-trial": [13, 53, 88, 186, 205], "matching": [14, 89, 103, 141, 206], "often": [15], "causing": [16], "delays": [17], "and": [18, 33, 66, 75, 107, 167, 183, 195, 216, 230, 241, 269], "failures.": [19], "Recent": [20], "advancements": [21, 234], "large": [23], "language": [24], "models": [25, 148], "(LLMs)": [26], "offer": [27], "promising": [29], "avenue": [30], "for": [31, 68], "automating": [32], "improving": [34], "this": [35, 135], "process.": [36], "This": [37], "scoping": [38], "review": [39], "aims": [40], "to": [41, 174, 212, 226, 258], "provide": [42], "comprehensive": [44, 57], "synthesis": [45], "of": [46, 50, 64, 132, 157, 218, 263], "the": [47, 111, 118, 129, 150, 214, 260], "emerging": [48], "applications": [49], "LLMs": [51, 86, 133, 264], "matching.": [54, 251], "METHODS:": [55], "A": [56], "search": [58], "was": [59], "conducted": [60], "PubMed,": [62], "Web": [63], "Science,": [65], "OpenAlex": [67], "literature": [69], "published": [70, 125], "between": [71], "December": [72, 76], "1,": [73], "2022,": [74], "31,": [77], "2024.": [78], "Studies": [79], "were": [80, 124], "included": [81, 160], "if": [82], "they": [83], "explicitly": [84], "integrated": [85], "into": [87], "systems.": [90], "Data": [91], "extraction": [92], "focused": [93], "on": [94, 197], "system": [95], "architectures,": [96], "patient": [97, 164, 267], "data": [98, 165, 199, 231, 243], "processing,": [99, 102, 163, 166], "eligibility": [100, 161], "criteria": [101, 162], "techniques,": [104], "evaluation": [105], "metrics,": [106], "performance.": [108], "RESULTS:": [109], "Of": [110], "2,357": [112], "studies": [113], "initially": [114], "identified,": [115], "24": [116], "met": [117], "inclusion": [119], "criteria.": [120], "The": [121], "majority": [122], "(21/24)": [123], "2024,": [127], "highlighting": [128], "rapid": [130], "adoption": [131], "domain.": [136], "Most": [137], "systems": [138, 159, 207], "used": [139, 153], "patient-centric": [140], "(17/24),": [142], "OpenAI's": [144], "generative": [145], "pretrained": [146], "transformer": [147], "being": [149], "most": [151], "commonly": [152], "LLM.": [154], "Core": [155], "components": [156], "these": [158, 253], "matching,": [168, 187], "some": [170], "incorporating": [171], "retrieval": [172], "algorithms": [173], "enhance": [175, 213], "computational": [176], "efficiency.": [177], "LLM-integrated": [178], "approaches": [179], "demonstrated": [180], "improved": [181], "accuracy": [182, 217], "scalability": [184], "although": [188], "challenges": [189, 254], "such": [190], "as": [191], "performance": [192], "variability,": [193], "interpretability,": [194], "reliance": [196], "synthetic": [198], "sets": [200], "remain": [201], "significant.": [202], "CONCLUSION:": [203], "LLM-based": [204, 249], "present": [208], "transformative": [210], "opportunity": [211], "efficiency": [215], "recruitment.": [221], "Despite": [222], "current": [223], "limitations": [224], "related": [225], "model": [227], "generalizability,": [228], "explainability,": [229], "constraints,": [232], "future": [233], "hybrid": [236], "modeling": [237], "strategies,": [238], "domain-specific": [239], "fine-tuning,": [240], "real-world": [242], "set": [244], "integration": [245], "could": [246], "further": [247], "optimize": [248], "Addressing": [252], "will": [255], "be": [256], "crucial": [257], "realizing": [259], "full": [261], "potential": [262], "streamlining": [266], "accelerating": [270], "execution.": [273]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9429000020027161, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, "topics": [{"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9429000020027161, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.024000000208616257, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10582", "display_name": "Ethics in Clinical Research", "score": 0.006800000090152025, "subfield": {"id": "https://openalex.org/subfields/2739", "display_name": "Public Health, Environmental and Occupational Health"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.1200/cci-25-00071", "is_oa": true, "landing_page_url": "https://doi.org/10.1200/cci-25-00071", "pdf_url": null, "source": {"id": "https://openalex.org/S4210181501", "display_name": "JCO Clinical Cancer Informatics", "issn_l": "2473-4276", "issn": ["2473-4276"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-1", "ki-jl-1", "medline", "norway-1"], "host_organization": "https://openalex.org/P4310315671", "host_organization_name": "Lippincott Williams & Wilkins", "host_organization_lineage": ["https://openalex.org/P4310315671", "https://openalex.org/P4310318547"], "host_organization_lineage_names": ["Lippincott Williams & Wilkins", "Wolters Kluwer"], "type": "journal"}, "license": "cc-by-nc-nd", "license_id": "https://openalex.org/licenses/cc-by-nc-nd", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "JCO Clinical Cancer Informatics", "raw_type": "journal-article"}, "cited_by_count": 9, "is_retracted": false}, {"id": "https://openalex.org/W7106689086", "doi": "https://doi.org/10.48550/arxiv.2511.19299", "title": "Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning", "publication_year": 2025, "publication_date": "2025-11-24", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Black, James R. M.", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I145311948", "display_name": "Johns Hopkins University", "ror": "https://ror.org/00za53h95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I145311948"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Black, James R. M.", "raw_affiliation_strings": ["Center for Health Security Johns Hopkins Bloomberg School of Public Health"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Center for Health Security Johns Hopkins Bloomberg School of Public Health", "institution_ids": ["https://openalex.org/I145311948"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Hanke, Moritz S.", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I145311948", "display_name": "Johns Hopkins University", "ror": "https://ror.org/00za53h95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I145311948"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Hanke, Moritz S.", "raw_affiliation_strings": ["Center for Health Security Johns Hopkins Bloomberg School of Public Health"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Center for Health Security Johns Hopkins Bloomberg School of Public Health", "institution_ids": ["https://openalex.org/I145311948"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Maiwald, Aaron", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I40120149", "display_name": "University of Oxford", "ror": "https://ror.org/052gg0110", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I40120149"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Maiwald, Aaron", "raw_affiliation_strings": ["Department of Chemistry University of Oxford"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Chemistry University of Oxford", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Hernandez-Boussard, Tina", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210137306", "display_name": "Stanford Medicine", "ror": "https://ror.org/03mtd9a03", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I4210137306", "https://openalex.org/I97018004"]}, {"id": "https://openalex.org/I97018004", "display_name": "Stanford University", "ror": "https://ror.org/00f54p054", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I97018004"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Hernandez-Boussard, Tina", "raw_affiliation_strings": ["Stanford University School of Medicine"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Stanford University School of Medicine", "institution_ids": ["https://openalex.org/I4210137306", "https://openalex.org/I97018004"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Crook, Oliver M.", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Crook, Oliver M.", "raw_affiliation_strings": ["Department of Chemistry & Kavli Institute for Nanoscience Discovery University of Oxford"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Chemistry & Kavli Institute for Nanoscience Discovery University of Oxford", "institution_ids": []}]}, {"author_position": "last", "author": {"id": null, "display_name": "Pannu, Jaspreet", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I145311948", "display_name": "Johns Hopkins University", "ror": "https://ror.org/00za53h95", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I145311948"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Pannu, Jaspreet", "raw_affiliation_strings": ["Center for Health Security Johns Hopkins Bloomberg School of Public Health"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Center for Health Security Johns Hopkins Bloomberg School of Public Health", "institution_ids": ["https://openalex.org/I145311948"]}]}], "abstract_inverted_index": {"Novel": [0], "deep": [1], "learning": [2], "architectures": [3], "are": [4], "increasingly": [5], "being": [6], "applied": [7], "to": [8, 17, 79, 127, 146, 181, 200, 227], "biological": [9], "data,": [10], "including": [11], "genetic": [12], "sequences.": [13, 158], "These": [14, 49], "models,": [15], "referred": [16], "as": [18], "genomic": [19, 72], "language": [20], "models": [21, 34, 100], "(gLMs),": [22], "have": [23, 51], "demonstrated": [24], "impressive": [25], "predictive": [26, 133], "and": [27, 117, 151, 217, 224], "generative": [28], "capabilities,": [29], "raising": [30], "concerns": [31, 50], "that": [32, 101, 189, 198], "such": [33], "may": [35], "also": [36, 165], "enable": [37, 228], "misuse,": [38], "for": [39, 46, 54, 97, 212, 215], "instance": [40], "via": [41], "the": [42, 129, 148, 210, 229], "generation": [43], "of": [44, 62, 66, 131, 175, 206, 232], "genomes": [45], "human-infecting": [47, 125, 163], "viruses.": [48], "catalyzed": [52], "calls": [53], "risk": [55], "mitigation": [56, 61, 225], "measures.": [57], "The": [58, 135, 159], "de": [59], "facto": [60], "choice": [63], "is": [64, 88, 96], "filtering": [65], "pretraining": [67], "data": [68, 190], "(i.e.,": [69], "removing": [70], "viral": [71, 143], "sequences": [73, 121, 144, 183], "from": [74, 122, 170], "training": [75], "datasets)": [76], "in": [77], "order": [78], "limit": [80], "gLM": [81], "performance": [82], "on": [83, 141, 156, 162, 222], "virus-related": [84], "tasks.": [85], "However,": [86], "it": [87], "not": [89], "currently": [90], "known": [91], "how": [92], "robust": [93], "this": [94], "approach": [95], "securing": [98], "open-source": [99], "can": [102], "be": [103, 193], "fine-tuned": [104, 136, 155, 161], "using": [105, 120], "sensitive": [106], "pathogen": [107], "data.": [108], "Here,": [109], "we": [110], "evaluate": [111], "a": [112, 153], "state-of-the-art": [113], "gLM,": [114], "Evo": [115], "2,": [116], "perform": [118], "fine-tuning": [119, 196], "110": [123], "harmful": [124], "viruses": [126, 164], "assess": [128], "rescue": [130, 203], "misuse-relevant": [132, 204], "capabilities.": [134], "model": [137, 150, 160], "exhibited": [138], "reduced": [139], "perplexity": [140], "unseen": [142], "relative": [145], "1)": [147], "pretrained": [149], "2)": [152], "version": [154], "bacteriophage": [157], "identified": [166], "immune": [167], "escape": [168], "variants": [169], "SARS-CoV-2": [171, 182], "(achieving": [172], "an": [173], "AUROC": [174], "0.6),": [176], "despite": [177], "having": [178], "no": [179], "exposure": [180], "during": [184], "fine-tuning.": [185], "This": [186], "work": [187, 220], "demonstrates": [188], "exclusion": [191], "might": [192], "circumvented": [194], "by": [195], "approaches": [197], "can,": [199], "some": [201], "degree,": [202], "capabilities": [205], "gLMs.": [207, 233], "We": [208], "highlight": [209], "need": [211], "safety": [213], "frameworks": [214], "gLMs": [216], "outline": [218], "further": [219], "needed": [221], "evaluations": [223], "measures": [226], "safe": [230], "deployment": [231]}, "primary_topic": {"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 0.9613999724388123, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 0.9613999724388123, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T13851", "display_name": "Law, AI, and Intellectual Property", "score": 0.01140000019222498, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10883", "display_name": "Ethics and Social Impacts of AI", "score": 0.0019000000320374966, "subfield": {"id": "https://openalex.org/subfields/3311", "display_name": "Safety Research"}, "field": {"id": "https://openalex.org/fields/33", "display_name": "Social Sciences"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.19299", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.19299", "pdf_url": "https://arxiv.org/pdf/2511.19299", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by-nc-sa", "license_id": "https://openalex.org/licenses/cc-by-nc-sa", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416542747", "doi": "https://doi.org/10.48550/arxiv.2504.12018", "title": "Instruction-augmented Multimodal Alignment for Image-Text and Element Matching", "publication_year": 2025, "publication_date": "2025-04-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101319605", "display_name": "Xinli Yue", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I37461747", "display_name": "Wuhan University", "ror": "https://ror.org/033vjfk17", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I37461747"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yue, Xinli", "raw_affiliation_strings": ["Wuhan University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Wuhan University", "institution_ids": ["https://openalex.org/I37461747"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Sun, JianHui", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, JianHui", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040066380", "display_name": "Junda Lu", "orcid": "https://orcid.org/0000-0002-8795-8697", "observed_orcids": ["https://orcid.org/0000-0002-8795-8697", "https://orcid.org/0009-0004-5450-0809"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lu, Junda", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yao, Liangchao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yao, Liangchao", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5078265090", "display_name": "Fan Xia", "orcid": "https://orcid.org/0000-0001-7705-4638", "observed_orcids": ["https://orcid.org/0000-0001-7705-4638", "https://orcid.org/0009-0005-8320-2963"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xia, Fan", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100399621", "display_name": "Tianyi Wang", "orcid": "https://orcid.org/0000-0001-6880-8194", "observed_orcids": ["https://orcid.org/0000-0001-6880-8194"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Tianyi", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076304703", "display_name": "Fengyun Rao", "orcid": "https://orcid.org/0000-0002-2868-2088", "observed_orcids": ["https://orcid.org/0000-0002-2868-2088"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rao, Fengyun", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076852517", "display_name": "Jing Lyu", "orcid": "https://orcid.org/0009-0008-9906-3162", "observed_orcids": ["https://orcid.org/0009-0008-9906-3162"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lyu, Jing", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5060932650", "display_name": "Yuetang Deng", "orcid": "https://orcid.org/0009-0003-7060-4109", "observed_orcids": ["https://orcid.org/0009-0003-7060-4109"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Deng, Yuetang", "raw_affiliation_strings": ["WeChat"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "WeChat", "institution_ids": []}]}], "abstract_inverted_index": {"With": [0], "the": [1, 10, 81, 118, 133, 151, 167, 177, 197], "rapid": [2], "advancement": [3], "of": [4, 43, 136, 169], "text-to-image": [5], "(T2I)": [6], "generation": [7], "models,": [8], "assessing": [9], "semantic": [11, 66], "alignment": [12, 67], "between": [13], "generated": [14], "images": [15], "and": [16, 40, 59, 160, 187], "text": [17], "descriptions": [18], "has": [19], "become": [20], "a": [21, 85, 103], "significant": [22], "research": [23], "challenge.": [24], "Current": [25], "methods,": [26, 183], "including": [27], "those": [28], "based": [29], "on": [30], "Visual": [31], "Question": [32], "Answering": [33], "(VQA),": [34], "still": [35], "struggle": [36], "with": [37], "fine-grained": [38], "assessments": [39], "precise": [41, 86], "quantification": [42], "image-text": [44, 65, 137], "alignment.": [45], "This": [46], "paper": [47], "presents": [48], "an": [49, 123, 140], "improved": [50], "evaluation": [51], "method": [52, 179], "named": [53], "Instruction-augmented": [54], "Multimodal": [55], "Alignment": [56], "for": [57], "Image-Text": [58, 211], "Element": [60], "Matching": [61], "(iMatch),": [62], "which": [63], "evaluates": [64], "by": [68], "fine-tuning": [69], "multimodal": [70, 94], "large": [71, 95], "language": [72, 96], "models.": [73], "We": [74], "introduce": [75], "four": [76], "innovative": [77], "augmentation": [78, 106, 125, 142, 159], "strategies:": [79], "First,": [80], "QAlign": [82], "strategy": [83, 107, 126, 143], "creates": [84], "probabilistic": [87], "mapping": [88], "to": [89, 113, 131, 149, 164, 202], "convert": [90], "discrete": [91], "scores": [92], "from": [93, 110], "models": [97], "into": [98], "continuous": [99], "matching": [100], "scores.": [101], "Second,": [102], "validation": [104], "set": [105], "uses": [108], "pseudo-labels": [109], "model": [111], "predictions": [112], "expand": [114], "training": [115], "data,": [116], "boosting": [117], "model's": [119, 134, 152], "generalization": [120], "performance.": [121], "Third,": [122], "element": [124, 128, 170], "integrates": [127], "category": [129], "labels": [130], "refine": [132], "understanding": [135], "matching.": [138], "Fourth,": [139], "image": [141], "employs": [144], "techniques": [145], "like": [146], "random": [147], "lighting": [148], "increase": [150], "robustness.": [153], "Additionally,": [154], "we": [155], "propose": [156], "prompt": [157], "type": [158], "score": [161], "perturbation": [162], "strategies": [163], "further": [165], "enhance": [166], "accuracy": [168], "assessments.": [171], "Our": [172], "experimental": [173], "results": [174], "show": [175], "that": [176], "iMatch": [178, 192], "significantly": [180], "surpasses": [181], "existing": [182], "confirming": [184], "its": [185], "effectiveness": [186], "practical": [188], "value.": [189], "Furthermore,": [190], "our": [191], "won": [193], "first": [194], "place": [195], "in": [196], "CVPR": [198], "NTIRE": [199], "2025": [200], "Text": [201], "Image": [203], "Generation": [204], "Model": [205], "Quality": [206], "Assessment": [207], "-": [208], "Track": [209], "1": [210], "Alignment.": [212]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9940999746322632, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9940999746322632, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "score": 0.00419999985024333, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10824", "display_name": "Image Retrieval and Classification Techniques", "score": 0.0005000000237487257, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2504.12018", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.12018", "pdf_url": "https://arxiv.org/pdf/2504.12018", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417357116", "doi": "https://doi.org/10.48550/arxiv.2506.10947", "title": "Spurious Rewards: Rethinking Training Signals in RLVR", "publication_year": 2025, "publication_date": "2025-06-12", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5047742348", "display_name": "Rulin Shao", "orcid": "https://orcid.org/0000-0002-8228-2106", "observed_orcids": ["https://orcid.org/0000-0002-8228-2106"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shao, Rulin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5022934996", "display_name": "Shuyue Stella Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Shuyue Stella", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101888897", "display_name": "Rui Xin", "orcid": "https://orcid.org/0000-0002-0224-3431", "observed_orcids": ["https://orcid.org/0000-0002-0224-3431"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xin, Rui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005776608", "display_name": "Scott Geng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Geng, Scott", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113844261", "display_name": "Yiping Wang", "orcid": "https://orcid.org/0000-0002-7540-6449", "observed_orcids": ["https://orcid.org/0000-0002-7540-6449"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yiping", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5028243041", "display_name": "Sewoong Oh", "orcid": "https://orcid.org/0000-0002-8975-8306", "observed_orcids": ["https://orcid.org/0000-0002-8975-8306"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Oh, Sewoong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5033061754", "display_name": "Simon S. Du", "orcid": "https://orcid.org/0000-0003-0056-8299", "observed_orcids": ["https://orcid.org/0000-0003-0056-8299"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Du, Simon Shaolei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5083548887", "display_name": "Nathan Lambert", "orcid": "https://orcid.org/0000-0002-9997-6817", "observed_orcids": ["https://orcid.org/0000-0002-9997-6817"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lambert, Nathan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039158419", "display_name": "Sewon Min", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Min, Sewon", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5032451496", "display_name": "Ranjay Krishna", "orcid": "https://orcid.org/0000-0001-8784-2531", "observed_orcids": ["https://orcid.org/0000-0001-8784-2531"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Krishna, Ranjay", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062910836", "display_name": "Yulia Tsvetkov", "orcid": "https://orcid.org/0000-0002-4634-7128", "observed_orcids": ["https://orcid.org/0000-0002-4634-7128"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tsvetkov, Yulia", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082305994", "display_name": "Hannaneh Hajishirzi", "orcid": "https://orcid.org/0000-0002-1055-6657", "observed_orcids": ["https://orcid.org/0000-0002-1055-6657"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hajishirzi, Hannaneh", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079904764", "display_name": "Pang Wei Koh", "orcid": "https://orcid.org/0000-0003-4330-6969", "observed_orcids": ["https://orcid.org/0000-0003-4330-6969"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Koh, Pang Wei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5067919401", "display_name": "Luke Zettlemoyer", "orcid": "https://orcid.org/0009-0008-8296-0764", "observed_orcids": ["https://orcid.org/0009-0008-8296-0764"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zettlemoyer, Luke", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0], "show": [1, 67], "that": [2, 22, 68, 142, 194], "reinforcement": [3], "learning": [4], "with": [5, 19, 30, 38, 125], "verifiable": [6], "rewards": [7, 21, 141, 193], "(RLVR)": [8], "can": [9, 79, 185], "elicit": [10], "strong": [11], "mathematical": [12], "reasoning": [13, 106, 108], "in": [14, 99, 109], "certain": [15], "language": [16], "models": [17, 147, 173, 189], "even": [18, 27, 86, 190], "spurious": [20, 126, 140], "have": [23], "little,": [24], "no,": [25], "or": [26, 160], "negative": [28], "correlation": [29], "the": [31, 55, 75, 129, 165], "correct": [32], "answer.": [33], "For": [34], "example,": [35], "RLVR": [36], "training": [37], "GRPO": [39, 69], "improves": [40], "MATH-500": [41], "performance": [42], "for": [43, 145, 153], "Qwen2.5-Math-7B": [44], "by": [45], "21.4": [46], "percentage": [47], "points": [48], "using": [49], "randomly": [50], "assigned": [51], "rewards,": [52], "nearly": [53], "matching": [54], "29.1-point": [56], "gain": [57], "from": [58, 74, 118, 191], "ground-truth": [59], "rewards.": [60, 89, 127], "To": [61], "explain": [62], "this": [63], "counterintuitive": [64], "observation,": [65], "we": [66, 94, 103], "exhibits": [70], "a": [71, 91, 178], "clipping": [72], "bias": [73], "clip": [76], "term,": [77], "which": [78, 102], "amplify": [80], "high-prior": [81], "behaviors": [82, 134], "learned": [83], "during": [84], "pretraining": [85], "without": [87, 111], "informative": [88], "As": [90], "case": [92], "study,": [93], "identify": [95], "one": [96], "such": [97, 132, 157], "behavior": [98], "Qwen2.5-Math": [100], "models,": [101], "call": [104], "code": [105, 110, 113], "--": [107], "actual": [112], "execution;": [114], "code-reasoning": [115], "frequency": [116], "increases": [117], "65": [119], "percent": [120, 124], "to": [121, 150], "over": [122], "90": [123], "However,": [128], "presence": [130], "of": [131, 167], "amplifiable": [133], "is": [135], "highly": [136], "model-dependent.": [137], "In": [138], "practice,": [139], "are": [143], "effective": [144], "Qwen": [146, 188], "often": [148], "fail": [149], "produce": [151], "gains": [152, 184], "other": [154], "model": [155], "families,": [156], "as": [158], "Llama3": [159], "OLMo2.": [161], "Our": [162], "results": [163], "highlight": [164], "importance": [166], "validating": [168], "RL": [169], "methods": [170], "across": [171], "diverse": [172], "rather": [174], "than": [175], "relying": [176], "on": [177, 187], "single": [179], "de": [180], "facto": [181], "choice:": [182], "large": [183], "arise": [186], "random": [192], "do": [195], "not": [196], "reflect": [197], "genuine": [198], "capability": [199], "improvements.": [200]}, "primary_topic": {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.4099000096321106, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.4099000096321106, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.11789999902248383, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.04749999940395355, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2506.10947", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.10947", "pdf_url": "https://arxiv.org/pdf/2506.10947", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7108664331", "doi": "https://doi.org/10.5281/zenodo.17817239", "title": "Deciphering the Pre-training Manifold for Optimal Fine-tuning Trajectories", "publication_year": 2025, "publication_date": "2025-12-04", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Revista, Zen", "orcid": "https://orcid.org/0009-0007-6299-2008", "observed_orcids": ["https://orcid.org/0009-0007-6299-2008"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Revista, Zen", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0007-6299-2008", "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "IA, 10", "orcid": "https://orcid.org/0009-0007-6299-2008", "observed_orcids": ["https://orcid.org/0009-0007-6299-2008"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "IA, 10", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0007-6299-2008", "affiliations": []}], "abstract_inverted_index": {"The": [0, 172], "paradigm": [1], "of": [2, 19, 35, 60, 74, 86, 99, 104, 113, 124, 169, 196, 204], "pre-training": [3, 67, 138, 198], "large": [4, 134], "models": [5], "on": [6, 12, 165], "extensive": [7], "datasets": [8], "followed": [9], "by": [10], "fine-tuning": [11, 36, 163, 186, 205, 213], "downstream": [13, 170], "tasks": [14], "has": [15], "become": [16], "a": [17, 41, 47, 102, 166, 193, 228, 241], "cornerstone": [18], "modern": [20], "artificial": [21], "intelligence.": [22], "Despite": [23], "its": [24, 79], "empirical": [25, 238], "success,": [26], "the": [27, 31, 51, 56, 61, 66, 72, 84, 93, 161, 197, 202], "underlying": [28], "mechanisms": [29], "governing": [30], "efficacy": [32], "and": [33, 83, 96, 111, 121, 137, 152, 156, 179, 207, 220], "trajectory": [34], "remain": [37], "largely": [38], "underexplored": [39], "from": [40], "geometrical": [42], "perspective.": [43], "This": [44, 224], "paper": [45], "proposes": [46], "comprehensive": [48], "investigation": [49], "into": [50, 147, 183], "\"pre-training": [52], "manifold,\"": [53], "defined": [54], "as": [55, 78], "intrinsic": [57, 80, 108], "geometric": [58, 154], "structure": [59], "feature": [62], "representations": [63], "learned": [64], "during": [65], "phase.": [68], "We": [69, 190], "hypothesize": [70], "that": [71, 192], "characteristics": [73], "this": [75, 125], "manifold,": [76], "such": [77], "dimensionality,": [81], "curvature,": [82], "distribution": [85], "task-relevant": [87], "information": [88], "within": [89], "it,": [90], "significantly": [91], "influence": [92], "speed,": [94], "stability,": [95], "ultimate": [97], "performance": [98], "fine-tuning.": [100], "Through": [101], "combination": [103], "manifold": [105, 126, 199], "learning": [106], "techniques,": [107], "dimension": [109], "estimators,": [110], "analysis": [112], "neural": [114], "tangent": [115], "kernels,": [116], "we": [117], "aim": [118], "to": [119, 217, 227], "map": [120], "quantify": [122], "properties": [123], "across": [127], "various": [128], "pre-trained": [129], "architectures": [130], "(e.g.,": [131], "vision": [132], "transformers,": [133], "language": [135], "models)": [136], "objectives.": [139], "Our": [140], "methodology": [141], "involves": [142], "projecting": [143], "high-dimensional": [144], "latent": [145], "spaces": [146], "lower-dimensional": [148], "representations,": [149], "analyzing": [150], "local": [151], "global": [153], "properties,": [155], "correlating": [157], "these": [158], "findings": [159], "with": [160], "observed": [162], "trajectories": [164], "diverse": [167], "set": [168], "tasks.": [171], "results": [173], "elucidate": [174], "how": [175], "features": [176], "are": [177], "organized": [178], "clustered,": [180], "providing": [181], "insights": [182], "why": [184], "certain": [185], "strategies": [187], "outperform": [188], "others.": [189], "demonstrate": [191], "deeper": [194], "understanding": [195], "allows": [200], "for": [201, 211, 233, 245], "prediction": [203], "difficulty": [206], "suggests": [208], "novel": [209], "approaches": [210], "manifold-aware": [212], "optimization,": [214], "potentially": [215], "leading": [216], "more": [218, 229], "efficient": [219], "robust": [221], "transfer": [222, 234], "learning.": [223], "work": [225], "contributes": [226], "principled": [230], "theoretical": [231], "foundation": [232], "learning,": [235], "moving": [236], "beyond": [237], "observations": [239], "towards": [240], "geometrically": [242], "informed": [243], "strategy": [244], "model": [246], "adaptation.": [247]}, "primary_topic": {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9945999979972839, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.9945999979972839, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11612", "display_name": "Stochastic Gradient Optimization Techniques", "score": 0.002099999925121665, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0010999999940395355, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.5281/zenodo.17817239", "is_oa": true, "landing_page_url": "https://doi.org/10.5281/zenodo.17817239", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400562", "display_name": "Zenodo (CERN European Organization for Nuclear Research)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I67311998", "host_organization_name": "European Organization for Nuclear Research", "host_organization_lineage": ["https://openalex.org/I67311998"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "JournalArticle"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7117355782", "doi": "https://doi.org/10.5281/zenodo.18062630", "title": "The Bottleneck Effect: Why Model Scaling Fails for Code Generation", "publication_year": 2025, "publication_date": "2025-12-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5121384347", "display_name": "Ashish Pandey", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4405255812", "display_name": "Khwopa College of Engineering", "ror": "https://ror.org/03et06q41", "country_code": "NP", "type": "education", "lineage": ["https://openalex.org/I155028946", "https://openalex.org/I4210129773", "https://openalex.org/I4405255812"]}, {"id": "https://openalex.org/I4405259083", "display_name": "Khwopa Engineering College", "ror": "https://ror.org/01q4qyd51", "country_code": "NP", "type": "education", "lineage": ["https://openalex.org/I4405259083"]}], "countries": ["NP"], "is_corresponding": true, "raw_author_name": "Pandey, Ashish", "raw_affiliation_strings": ["Khwopa College of Engineering"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Khwopa College of Engineering", "institution_ids": ["https://openalex.org/I4405255812", "https://openalex.org/I4405259083"]}]}], "abstract_inverted_index": {"Scaling": [0], "language": [1, 12], "models": [2, 153], "from": [3], "124M": [4], "to": [5, 32], "355M": [6], "parameters": [7], "improves": [8], "performance": [9], "across": [10, 50, 82], "natural": [11], "tasks,": [13], "yet": [14], "we": [15, 55, 92], "observe": [16], "the": [17, 39, 57], "opposite": [18], "for": [19, 34, 173], "code": [20, 52, 148], "generation.": [21], "GPT-2": [22, 35, 60, 98], "Medium": [23, 61, 99], "(355M)": [24], "achieves": [25, 42], "only": [26], "4.8%": [27], "success": [28, 112], "on": [29], "HumanEval": [30], "compared": [31], "5.2%": [33], "Small": [36], "(124M),": [37], "while": [38, 78], "similarly-sized": [40], "CodeGen-350M": [41], "37.4%": [43], "success.": [44], "Through": [45], "systematic": [46], "layer-wise": [47], "ablation": [48], "experiments": [49], "16,300-16,400": [51], "generation": [53, 149], "attempts,": [54], "reveal": [56], "architectural": [58, 142], "cause:": [59], "exhibits": [62], "extreme": [63], "processing": [64, 81], "bottlenecks,": [65], "routing": [66], "all": [67], "computation": [68], "through": [69], "single": [70, 159], "critical": [71, 85, 117], "layers": [72, 86], "(Layer": [73], "12": [74, 129], "at": [75, 103], "50%": [76], "depth),": [77], "CodeGen": [79, 109], "distributes": [80], "multiple": [83], "redundant": [84], "(Layers": [87], "5,": [88], "7,": [89], "13).": [90], "When": [91], "ablate": [93], "(zero": [94], "out)": [95], "individual": [96], "layers,": [97], "shows": [100], "catastrophic": [101], "failure": [102], "its": [104, 115], "bottleneck": [105], "(0%": [106], "success),": [107], "whereas": [108], "maintains": [110], "29.5%": [111], "even": [113], "with": [114, 134, 151], "most": [116], "layer": [118], "removed.": [119], "We": [120], "further": [121], "identify": [122], "five": [123], "specific": [124], "activation": [125], "dimensions": [126], "in": [127], "Layer": [128], "that": [130, 157], "encode": [131], "syntactic": [132], "correctness": [133], "71.5%": [135], "accuracy.": [136], "Our": [137], "mechanistic": [138], "analysis": [139], "explains": [140], "why": [141], "choices": [143], "during": [144], "pretraining\u2014not": [145], "parameter": [146], "count\u2014determine": [147], "capability,": [150], "code-pretrained": [152], "developing": [154], "distributed": [155], "representations": [156], "prevent": [158], "points": [160], "of": [161], "failure.": [162], "These": [163], "findings": [164], "challenge": [165], "conventional": [166], "scaling": [167], "assumptions": [168], "and": [169], "provide": [170], "design": [171], "principles": [172], "robust": [174], "code-generating": [175], "architectures.": [176]}, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.8895999789237976, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.8895999789237976, "subfield": {"id": "https://openalex.org/subfields/1710", "display_name": "Information Systems"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.09149999916553497, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.005900000222027302, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.5281/zenodo.18062630", "is_oa": true, "landing_page_url": "https://doi.org/10.5281/zenodo.18062630", "pdf_url": null, "source": {"id": "https://openalex.org/S4306400562", "display_name": "Zenodo (CERN European Organization for Nuclear Research)", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I67311998", "host_organization_name": "European Organization for Nuclear Research", "host_organization_lineage": ["https://openalex.org/I67311998"], "host_organization_lineage_names": [], "type": "repository"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": null, "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "Preprint"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7128398599", "doi": "https://doi.org/10.46647/xvszab68", "title": "A Cross-Domain Knowledge-Enhanced Framework for Fine-Grained Emotion-Cause Pair Extraction with Optimized Pre-training", "publication_year": 2025, "publication_date": "2025-11-24", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5125382443", "display_name": "B. Praveen Kumar", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "B. Kranthi Kumar", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5125388279", "display_name": "Prof. S. Aquter Babu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Prof. S. Aquter Babu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Textual": [0], "Emotion": [1, 31], "Cause": [2, 32], "Extraction": [3, 33, 61], "(TECE)": [4], "has": [5], "emerged": [6], "as": [7], "a": [8, 97, 196, 204, 213, 225], "critical": [9, 368], "task": [10], "in": [11, 23, 78, 341, 350], "natural": [12], "language": [13, 182], "processing,": [14], "enabling": [15, 124], "systems": [16], "to": [17], "identify": [18], "not": [19], "only": [20], "emotions": [21, 44], "expressed": [22], "text": [24], "but": [25], "also": [26], "their": [27, 55], "underlying": [28], "causes.": [29], "Traditional": [30], "(ECE)": [34], "methods": [35], "suffer": [36], "from": [37, 161], "two": [38], "fundamental": [39], "limitations:": [40], "dependency": [41], "on": [42, 255, 275, 284, 291, 333], "pre-annotated": [43], "and": [45, 51, 90, 117, 134, 146, 166, 174, 188, 224, 232, 249, 289, 309, 344, 360, 378], "separate": [46], "handling": [47, 327, 380], "of": [48, 273, 328, 381], "emotion": [49, 116, 167], "recognition": [50], "cause": [52, 118], "extraction,": [53, 83], "neglecting": [54], "interdependent": [56], "nature.": [57], "While": [58], "Emotion-Cause": [59], "Pair": [60], "(ECPE)": [62], "addresses": [63, 367], "these": [64], "issues": [65], "through": [66, 105, 169, 246], "joint": [67], "detection,": [68], "current": [69], "state-of-the-art": [70, 340], "approaches": [71], "face": [72], "persistent": [73], "challenges": [74], "including": [75], "error": [76], "propagation": [77], "two-step": [79], "pipelines,": [80], "coarse-grained": [81], "clause-level": [82], "limited": [84], "cross-domain": [85, 99, 128, 262, 285, 306], "generalization,": [86], "insufficient": [87], "knowledge": [88, 151, 162, 300, 323], "integration,": [89], "suboptimal": [91], "pre-training": [92, 177, 311], "strategies.": [93], "This": [94, 336], "paper": [95], "proposes": [96], "novel": [98], "knowledge-enhanced": [100], "framework": [101, 194, 267, 366], "that": [102, 113, 265, 299], "advances": [103, 338], "ECPE": [104, 277], "four": [106], "key": [107], "innovations:": [108], "(1)": [109], "fine-grained": [110, 314, 375], "span-level": [111, 292], "extraction": [112, 293, 315], "identifies": [114], "precise": [115, 318], "phrases": [119], "rather": [120], "than": [121], "entire": [122], "clauses,": [123], "aspect-level": [125, 319], "analysis;": [126], "(2)": [127], "adaptation": [129, 243, 307], "mechanisms": [130], "combining": [131, 179], "adversarial": [132], "training": [133], "domain-invariant": [135], "feature": [136], "learning": [137, 187], "for": [138, 211, 221, 348, 371], "effective": [139, 379], "transfer": [140], "across": [141, 373], "news,": [142], "social": [143, 357], "media,": [144], "reviews,": [145], "conversational": [147], "domains;": [148], "(3)": [149], "multi-source": [150], "injection": [152], "architecture": [153, 199], "integrating": [154], "linguistic": [155], "patterns,": [156], "discourse": [157, 189], "relations,": [158], "commonsense": [159, 240], "reasoning": [160], "bases": [163], "(ConceptNet,": [164], "ATOMIC),": [165], "lexicons": [168], "knowledge-aware": [170], "graph": [171], "attention": [172, 231], "networks;": [173], "(4)": [175], "optimized": [176, 310], "strategy": [178], "domain-adaptive": [180], "masked": [181], "modeling": [183], "with": [184, 200, 217, 239], "emotion-aware": [185], "contrastive": [186], "relation": [190], "prediction.": [191], "The": [192, 313, 364], "proposed": [193, 365], "employs": [195], "unified": [197], "end-to-end": [198], "three": [201], "core": [202], "modules:": [203], "Knowledge-Optimized": [205], "Pre-training": [206], "Layer": [207, 228], "using": [208, 229], "customized": [209], "objectives": [210], "TECE,": [212], "Span-Level": [214], "ECE": [215], "Module": [216], "multi-task": [218], "BIO": [219], "tagging": [220], "emotion/cause/aspect": [222], "spans,": [223], "Knowledge-Enhanced": [226], "Reasoning": [227], "dependency-based": [230], "knowledge-guided": [233], "GAT": [234], "over": [235, 281], "clause": [236], "graphs": [237], "enriched": [238], "concepts.": [241], "Cross-domain": [242], "is": [244], "achieved": [245], "domain": [247], "discriminators": [248], "parameter-efficient": [250], "domain-specific": [251], "adapters.": [252], "Comprehensive": [253], "experiments": [254], "benchmark": [256], "datasets": [257], "(ECPE-news,": [258], "enhanced": [259], "English": [260], "ECPE,": [261], "corpora)": [263], "demonstrate": [264], "our": [266], "achieves": [268], "significant": [269], "improvements:": [270], "F1": [271, 304], "scores": [272], "74.6%": [274], "standard": [276], "tasks": [278], "(4.2%": [279], "improvement": [280, 332], "state-of-the-art),": [282], "71.8%": [283], "scenarios": [286], "(6.8%": [287], "improvement),": [288], "78.3%": [290], "(5.1%": [294], "improvement).": [295], "Ablation": [296], "studies": [297], "validate": [298], "enhancement": [301, 324], "contributes": [302], "2.8%": [303], "gain,": [305], "3.2%,": [308], "2.1%.": [312], "capability": [316], "enables": [317], "emotion-cause": [320, 342, 384], "analysis,": [321], "while": [322], "significantly": [325], "improves": [326], "implicit": [329, 334, 383], "causality": [330], "(8.4%": [331], "examples).": [335], "work": [337], "the": [339], "analysis": [343], "establishes": [345], "practical": [346], "foundations": [347], "deployment": [349], "mental": [351], "health": [352], "monitoring,": [353], "customer": [354], "experience": [355], "management,": [356], "media": [358], "analytics,": [359], "intelligent": [361], "dialogue": [362], "systems.": [363], "real-world": [369], "requirements": [370], "robustness": [372], "domains,": [374], "actionable": [376], "insights,": [377], "complex": [382], "relationships.": [385]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9932000041007996, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.9932000041007996, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.0044999998062849045, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10667", "display_name": "Emotion and Mood Recognition", "score": 0.0010000000474974513, "subfield": {"id": "https://openalex.org/subfields/3205", "display_name": "Experimental and Cognitive Psychology"}, "field": {"id": "https://openalex.org/fields/32", "display_name": "Psychology"}, "domain": {"id": "https://openalex.org/domains/2", "display_name": "Social Sciences"}}], "primary_location": {"id": "doi:10.46647/xvszab68", "is_oa": true, "landing_page_url": "https://doi.org/10.46647/xvszab68", "pdf_url": "https://rdems.in/index.php/RDEMS/article/download/22/21", "source": {"id": "https://openalex.org/S5407056652", "display_name": "Research Digest on Engineering Management and Social Innovations", "issn_l": "3117-4426", "issn": ["3117-4426"], "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": [], "host_organization_lineage_names": [], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Research Digest on Engineering Management and Social Innovations", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4409531322", "doi": "https://doi.org/10.2139/ssrn.5219321", "title": "Automated TNM Staging of Gastric Cancer Using Large Language Models: A Multicenter Study", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113781931", "display_name": "Xujie Gao", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xujie Gao", "raw_affiliation_strings": ["Tianjin Medical University - Department of Radiology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Department of Radiology", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100383772", "display_name": "Jiaxin Liu", "orcid": "https://orcid.org/0000-0003-3508-9132", "observed_orcids": ["https://orcid.org/0000-0003-3508-9132", "https://orcid.org/0009-0002-3547-7880", "https://orcid.org/0009-0005-0162-3554"]}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiaxin Liu", "raw_affiliation_strings": ["Tianjin Medical University - Key Laboratory of Cancer Prevention and Therapy"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Key Laboratory of Cancer Prevention and Therapy", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100364335", "display_name": "Yanhui Zhang", "orcid": "https://orcid.org/0000-0002-2179-2065", "observed_orcids": ["https://orcid.org/0000-0002-2179-2065"]}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yanhui Zhang", "raw_affiliation_strings": ["Tianjin Medical University - Department of Pathology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Department of Pathology", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Lingwei Wang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lingwei Wang", "raw_affiliation_strings": ["Tianjin Medical University - Department of Radiology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Department of Radiology", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5060489720", "display_name": "Tingting Ma", "orcid": "https://orcid.org/0009-0005-8662-781X", "observed_orcids": ["https://orcid.org/0009-0005-8662-781X"]}, "institutions": [{"id": "https://openalex.org/I4210142182", "display_name": "Tianjin Hospital", "ror": "https://ror.org/04j9yn198", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210142182"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tingting Ma", "raw_affiliation_strings": ["Tianjin Hospital"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Hospital", "institution_ids": ["https://openalex.org/I4210142182"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113168574", "display_name": "Tao Song", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210093484", "display_name": "Tianjin Nankai Hospital", "ror": "https://ror.org/00hq79z10", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210093484"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tao Song", "raw_affiliation_strings": ["Tianjin Nankai Hospital", "Tianjin Nankai Hospital, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Nankai Hospital", "institution_ids": ["https://openalex.org/I4210093484"]}, {"raw_affiliation_string": "Tianjin Nankai Hospital, China", "institution_ids": ["https://openalex.org/I4210093484"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100365175", "display_name": "Bin Li", "orcid": "https://orcid.org/0000-0002-3769-7476", "observed_orcids": ["https://orcid.org/0000-0002-3769-7476"]}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Bin Li", "raw_affiliation_strings": ["Tianjin Medical University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5108587296", "display_name": "Jingli Cui", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jingli Cui", "raw_affiliation_strings": ["Shandong Second Medical University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shandong Second Medical University", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5069910063", "display_name": "Yan Sun", "orcid": "https://orcid.org/0000-0002-3974-1645", "observed_orcids": ["https://orcid.org/0000-0002-3974-1645"]}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yan Sun", "raw_affiliation_strings": ["Tianjin Medical University - Department of Pathology"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Department of Pathology", "institution_ids": ["https://openalex.org/I5740404"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5090286598", "display_name": "Zhaoxiang Ye", "orcid": "https://orcid.org/0000-0003-3157-8393", "observed_orcids": ["https://orcid.org/0000-0003-3157-8393"]}, "institutions": [{"id": "https://openalex.org/I5740404", "display_name": "Tianjin Medical University", "ror": "https://ror.org/02mh8wx89", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I5740404"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhaoxiang Ye", "raw_affiliation_strings": ["Tianjin Medical University - Department of Radiology", "Tianjin Medical University - Department of Radiology, Huanhu, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tianjin Medical University - Department of Radiology", "institution_ids": ["https://openalex.org/I5740404"]}, {"raw_affiliation_string": "Tianjin Medical University - Department of Radiology, Huanhu, China", "institution_ids": ["https://openalex.org/I5740404"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.350600004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T13702", "display_name": "Machine Learning in Healthcare", "score": 0.350600004196167, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10696", "display_name": "Gastric Cancer Management and Outcomes", "score": 0.21699999272823334, "subfield": {"id": "https://openalex.org/subfields/2740", "display_name": "Pulmonary and Respiratory Medicine"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.1526000052690506, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.2139/ssrn.5219321", "is_oa": true, "landing_page_url": "https://doi.org/10.2139/ssrn.5219321", "pdf_url": null, "source": {"id": "https://openalex.org/S4210172589", "display_name": "SSRN Electronic Journal", "issn_l": "1556-5068", "issn": ["1556-5068"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I1318003438", "host_organization_name": "RELX Group (Netherlands)", "host_organization_lineage": ["https://openalex.org/I1318003438"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": null, "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7117078737", "doi": null, "title": "Do Foundational Audio Encoders Understand Music Structure?", "publication_year": 2025, "publication_date": "2025-12-19", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Toyama, Keisuke", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Toyama, Keisuke", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042128373", "display_name": "Zhi Fang Zhong", "orcid": "https://orcid.org/0000-0001-7703-9446", "observed_orcids": ["https://orcid.org/0000-0001-7703-9446"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhong, Zhi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Takahashi, Akira", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Takahashi, Akira", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5021350698", "display_name": "Shusuke Takahashi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Takahashi, Shusuke", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5088754502", "display_name": "Yuki Mitsufuji", "orcid": "https://orcid.org/0000-0002-6806-6140", "observed_orcids": ["https://orcid.org/0000-0002-6806-6140"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mitsufuji, Yuki", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"In": [0, 87], "music": [1, 25, 40, 44, 50, 120], "information": [2], "retrieval": [3], "(MIR)": [4], "research,": [5], "the": [6, 68, 130], "use": [7, 48], "of": [8, 24, 60, 70, 97], "pretrained": [9, 20], "foundational": [10], "audio": [11, 27], "encoders": [12], "(FAEs)": [13], "has": [14, 62], "recently": [15], "become": [16], "a": [17, 57], "trend.": [18], "FAEs": [19, 61, 98, 111], "on": [21, 35, 82, 94, 119], "large": [22], "amounts": [23], "and": [26, 42, 67, 78, 137], "data": [28, 121], "have": [29], "been": [30, 63], "shown": [31], "to": [32, 99], "improve": [33], "performance": [34, 84], "MIR": [36], "tasks": [37], "such": [38, 72], "as": [39, 73], "tagging": [41], "automatic": [43], "transcription.": [45], "However,": [46], "their": [47], "for": [49, 65, 125, 132], "structure": [51], "analysis": [52], "(MSA)": [53], "remains": [54, 85], "underexplored:": [55], "only": [56], "small": [58], "subset": [59], "examined": [64], "MSA,": [66], "impact": [69], "factors": [71, 103], "learning": [74, 114], "methods,": [75], "training": [76], "data,": [77], "model": [79], "context": [80], "length": [81], "MSA": [83, 105], "unclear.": [86], "this": [88], "study,": [89], "we": [90], "conduct": [91], "comprehensive": [92], "experiments": [93], "11": [95], "types": [96], "investigate": [100], "how": [101], "these": [102], "affect": [104], "performance.": [106], "Our": [107], "results": [108], "demonstrate": [109], "that": [110], "using": [112], "self-supervised": [113], "with": [115], "masked": [116], "language": [117], "modeling": [118], "are": [122], "particularly": [123], "effective": [124], "MSA.": [126, 138], "These": [127], "findings": [128], "pave": [129], "way": [131], "future": [133], "research": [134], "in": [135], "FAE": [136]}, "primary_topic": {"id": "https://openalex.org/T11309", "display_name": "Music and Audio Processing", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1711", "display_name": "Signal Processing"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11309", "display_name": "Music and Audio Processing", "score": 1.0, "subfield": {"id": "https://openalex.org/subfields/1711", "display_name": "Signal Processing"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11349", "display_name": "Music Technology and Sound Studies", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10788", "display_name": "Neuroscience and Music Perception", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/2805", "display_name": "Cognitive Neuroscience"}, "field": {"id": "https://openalex.org/fields/28", "display_name": "Neuroscience"}, "domain": {"id": "https://openalex.org/domains/1", "display_name": "Life Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2512.17209", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.17209", "pdf_url": "https://arxiv.org/pdf/2512.17209", "source": {"id": "https://openalex.org/S4306400194", "display_name": "arXiv (Cornell University)", "issn_l": "2331-8422", "issn": ["2331-8422"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I205783295", "host_organization_name": "Cornell University", "host_organization_lineage": ["https://openalex.org/I205783295"], "host_organization_lineage_names": [], "type": "repository"}, "license": null, "license_id": null, "version": "submittedVersion", "is_accepted": false, "is_published": false, "raw_source_name": null, "raw_type": "text"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4415182798", "doi": "https://doi.org/10.1016/j.bspc.2025.109251", "title": "MedPrompt: LLM\u2013CNN Fusion with Weight Routing for Medical Image Segmentation and Classification", "publication_year": 2025, "publication_date": "2025-11-21", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5117837738", "display_name": "Shadman Sobhan", "orcid": "https://orcid.org/0009-0003-9715-8049", "observed_orcids": ["https://orcid.org/0009-0003-9715-8049"]}, "institutions": [{"id": "https://openalex.org/I183697816", "display_name": "Bangladesh University of Engineering and Technology", "ror": "https://ror.org/05a1qpv97", "country_code": "BD", "type": "education", "lineage": ["https://openalex.org/I183697816"]}], "countries": ["BD"], "is_corresponding": false, "raw_author_name": "Shadman Sobhan", "raw_affiliation_strings": ["Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh"], "raw_orcid": "https://orcid.org/0009-0003-9715-8049", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh", "institution_ids": ["https://openalex.org/I183697816"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Kazi Abrar Mahmud", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I183697816", "display_name": "Bangladesh University of Engineering and Technology", "ror": "https://ror.org/05a1qpv97", "country_code": "BD", "type": "education", "lineage": ["https://openalex.org/I183697816"]}], "countries": ["BD"], "is_corresponding": false, "raw_author_name": "Kazi Abrar Mahmud", "raw_affiliation_strings": ["Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh", "institution_ids": ["https://openalex.org/I183697816"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5098790304", "display_name": "Abduz Zami", "orcid": "https://orcid.org/0009-0009-9679-0900", "observed_orcids": ["https://orcid.org/0009-0009-9679-0900"]}, "institutions": [{"id": "https://openalex.org/I17477748", "display_name": "Rajshahi University of Engineering and Technology", "ror": "https://ror.org/049ysg747", "country_code": "BD", "type": "education", "lineage": ["https://openalex.org/I17477748"]}], "countries": ["BD"], "is_corresponding": false, "raw_author_name": "Abduz Zami", "raw_affiliation_strings": ["Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh"], "raw_orcid": "https://orcid.org/0009-0009-9679-0900", "affiliations": [{"raw_affiliation_string": "Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh", "institution_ids": ["https://openalex.org/I17477748"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Mohiuddin Ahmed", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I17477748", "display_name": "Rajshahi University of Engineering and Technology", "ror": "https://ror.org/049ysg747", "country_code": "BD", "type": "education", "lineage": ["https://openalex.org/I17477748"]}], "countries": ["BD"], "is_corresponding": false, "raw_author_name": "Mohiuddin Ahmed", "raw_affiliation_strings": ["Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh", "institution_ids": ["https://openalex.org/I17477748"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Md Palash Uddin", "orcid": "https://orcid.org/0000-0002-4429-6590", "observed_orcids": ["https://orcid.org/0000-0002-4429-6590"]}, "institutions": [{"id": "https://openalex.org/I149704539", "display_name": "Deakin University", "ror": "https://ror.org/02czsnj07", "country_code": "AU", "type": "education", "lineage": ["https://openalex.org/I149704539"]}, {"id": "https://openalex.org/I197842652", "display_name": "Hajee Mohammad Danesh Science and Technology University", "ror": "https://ror.org/00kvxt616", "country_code": "BD", "type": "education", "lineage": ["https://openalex.org/I197842652"]}], "countries": ["AU", "BD"], "is_corresponding": true, "raw_author_name": "Md Palash Uddin", "raw_affiliation_strings": ["Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, 5200, Bangladesh", "School of Information Technology, Deakin University, Geelong, VIC 3220, Australia"], "raw_orcid": "https://orcid.org/0000-0002-4429-6590", "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, 5200, Bangladesh", "institution_ids": ["https://openalex.org/I197842652"]}, {"raw_affiliation_string": "School of Information Technology, Deakin University, Geelong, VIC 3220, Australia", "institution_ids": ["https://openalex.org/I149704539"]}]}], "abstract_inverted_index": {"Most": [0], "existing": [1], "medical": [2, 30, 210], "image": [3, 93, 211], "analysis": [4, 212], "systems": [5], "are": [6], "task-specific,": [7], "requiring": [8], "separate": [9], "models": [10], "for": [11, 38, 83, 92, 125, 175, 189, 197, 208], "classification": [12, 192], "and": [13, 15, 47, 52, 71, 100, 107, 131, 134, 148, 160, 191, 205], "segmentation,": [14], "lack": [16], "the": [17, 36, 53, 123], "flexibility": [18], "to": [19, 57, 112], "support": [20], "user-defined": [21], "workflows": [22], "expressed": [23], "in": [24, 158], "natural": [25, 162], "language.": [26], "Developing": [27], "a": [28, 69, 76, 87, 202, 214], "prompt-driven": [29, 209], "assistant": [31], "introduces": [32], "significant": [33], "challenges,": [34, 65], "including": [35], "need": [37, 124], "large": [39], "annotated": [40], "datasets,": [41], "integration": [42], "of": [43, 55, 170, 217], "multimodal": [44], "data": [45], "(text": [46], "images),": [48], "high": [49], "computational": [50], "demands,": [51], "difficulty": [54], "adapting": [56], "diverse": [58], "tasks": [59, 130, 147], "without": [60], "retraining.": [61], "To": [62], "address": [63], "these": [64], "we": [66, 115], "present": [67], "MedPrompt,": [68], "unified": [70], "extensible": [72], "framework": [73], "that": [74], "combines": [75], "few-shot": [77], "prompted": [78], "Large": [79], "Language": [80], "Model": [81], "(LlaMA-4-17B)": [82], "task": [84, 136], "planning": [85], "with": [86, 165], "modular": [88], "CNN": [89], "architecture": [90], "(DeepFusionLab)": [91], "analysis.": [94], "The": [95, 152], "LLM": [96], "parses": [97], "user": [98], "instructions": [99], "generates": [101], "structured": [102], "JSON": [103], "workflows,": [104], "dynamically": [105], "selecting": [106], "routing": [108, 119], "task-specific": [109], "pretrained": [110], "weights": [111], "DeepFusionLab\u2014a": [113], "strategy": [114], "term": [116], "dynamic": [117], "weight": [118], ".": [120], "This": [121], "eliminates": [122], "retraining": [126], "when": [127], "adding": [128], "new": [129], "supports": [132], "multi-stage": [133], "conditional": [135], "execution.": [137], "We": [138], "evaluate": [139], "MedPrompt": [140, 200], "on": [141, 173], "19": [142], "public": [143], "datasets": [144], "across": [145, 213], "12": [146], "5": [149], "imaging": [150], "modalities.": [151], "system": [153], "achieves": [154], "97%": [155], "end-to-end": [156], "correctness": [157], "interpreting": [159], "executing": [161], "language": [163], "prompts,": [164], "an": [166], "average": [167], "inference": [168], "latency": [169], "2.5": [171], "s": [172], "CPU\u2014suitable": [174], "near": [176], "real-time": [177], "clinical": [178, 218], "applications.": [179], "DeepFusionLab": [180], "demonstrates": [181], "strong": [182], "segmentation": [183], "accuracy": [184], "(e.g.,": [185], "Dice": [186], "\u223c": [187, 195], "0.9856": [188], "lungs)": [190], "performance": [193], "(F1": [194], "0.9744": [196], "tuberculosis).": [198], "Overall,": [199], "offers": [201], "scalable,": [203], "interpretable,": [204], "deployment-ready": [206], "solution": [207], "wide": [215], "range": [216], "scenarios.": [219]}, "primary_topic": {"id": "https://openalex.org/T10052", "display_name": "Medical Image Segmentation Techniques", "score": 0.35740000009536743, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T10052", "display_name": "Medical Image Segmentation Techniques", "score": 0.35740000009536743, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.2734000086784363, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.24650000035762787, "subfield": {"id": "https://openalex.org/subfields/2718", "display_name": "Health Informatics"}, "field": {"id": "https://openalex.org/fields/27", "display_name": "Medicine"}, "domain": {"id": "https://openalex.org/domains/4", "display_name": "Health Sciences"}}], "primary_location": {"id": "doi:10.1016/j.bspc.2025.109251", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.bspc.2025.109251", "pdf_url": null, "source": {"id": "https://openalex.org/S8427965", "display_name": "Biomedical Signal Processing and Control", "issn_l": "1746-8094", "issn": ["1746-8094", "1746-8108"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1", "ki-jl-1", "norway-1"], "host_organization": "https://openalex.org/P4310320990", "host_organization_name": "Elsevier BV", "host_organization_lineage": ["https://openalex.org/P4310320990"], "host_organization_lineage_names": ["Elsevier BV"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Biomedical Signal Processing and Control", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4408272594", "doi": "https://doi.org/10.1007/s13755-025-00341-x", "title": "Hyperbolic vision language representation learning on chest radiology images", "publication_year": 2025, "publication_date": "2025-03-09", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5108134630", "display_name": "Zuojing Zhang", "orcid": "https://orcid.org/0000-0003-2131-6381", "observed_orcids": ["https://orcid.org/0000-0003-2131-6381"]}, "institutions": [{"id": "https://openalex.org/I183067930", "display_name": "Shanghai Jiao Tong University", "ror": "https://ror.org/0220qvk04", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183067930"]}, {"id": "https://openalex.org/I2802608112", "display_name": "Shanghai Chest Hospital", "ror": "https://ror.org/03fjc3817", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I2802608112"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zuojing Zhang", "raw_affiliation_strings": ["Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030 China", "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030 China", "institution_ids": ["https://openalex.org/I183067930", "https://openalex.org/I2802608112"]}, {"raw_affiliation_string": "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China", "institution_ids": ["https://openalex.org/I183067930", "https://openalex.org/I2802608112"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5000889530", "display_name": "Zhi Qiao", "orcid": "https://orcid.org/0000-0002-3095-3908", "observed_orcids": ["https://orcid.org/0000-0002-3095-3908"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhi Qiao", "raw_affiliation_strings": ["Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080 China", "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080 China", "institution_ids": []}, {"raw_affiliation_string": "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5108994113", "display_name": "Linbin Han", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Linbin Han", "raw_affiliation_strings": ["School of Physics, Peking University, Beijing, 100080 China", "School of Physics, Peking University, Beijing, 100080, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Physics, Peking University, Beijing, 100080 China", "institution_ids": ["https://openalex.org/I20231570"]}, {"raw_affiliation_string": "School of Physics, Peking University, Beijing, 100080, China", "institution_ids": ["https://openalex.org/I20231570"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101950118", "display_name": "Hong Bing Yang", "orcid": "https://orcid.org/0000-0003-2361-0437", "observed_orcids": ["https://orcid.org/0000-0003-2361-0437", "https://orcid.org/0000-0002-4328-335X"]}, "institutions": [{"id": "https://openalex.org/I37987034", "display_name": "Guangzhou University", "ror": "https://ror.org/05ar8rn06", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I37987034"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hong Yang", "raw_affiliation_strings": ["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006 China", "Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006 China", "institution_ids": ["https://openalex.org/I37987034"]}, {"raw_affiliation_string": "Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006, China", "institution_ids": ["https://openalex.org/I37987034"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhen Qian", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Zhen Qian", "raw_affiliation_strings": ["Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080 China", "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080 China", "institution_ids": []}, {"raw_affiliation_string": "Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Beijing, 100080, China", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5007934995", "display_name": "Jingxiang Wu", "orcid": "https://orcid.org/0000-0002-2858-9668", "observed_orcids": ["https://orcid.org/0000-0002-2858-9668"]}, "institutions": [{"id": "https://openalex.org/I183067930", "display_name": "Shanghai Jiao Tong University", "ror": "https://ror.org/0220qvk04", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I183067930"]}, {"id": "https://openalex.org/I2802608112", "display_name": "Shanghai Chest Hospital", "ror": "https://ror.org/03fjc3817", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I2802608112"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jingxiang Wu", "raw_affiliation_strings": ["Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030 China", "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030 China", "institution_ids": ["https://openalex.org/I183067930", "https://openalex.org/I2802608112"]}, {"raw_affiliation_string": "Department of Anesthesiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China", "institution_ids": ["https://openalex.org/I183067930", "https://openalex.org/I2802608112"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9990000128746033, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10824", "display_name": "Image Retrieval and Classification Techniques", "score": 0.00039999998989515007, "subfield": {"id": "https://openalex.org/subfields/1707", "display_name": "Computer Vision and Pattern Recognition"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 9.999999747378752e-05, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1007/s13755-025-00341-x", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s13755-025-00341-x", "pdf_url": null, "source": {"id": "https://openalex.org/S4210178793", "display_name": "Health Information Science and Systems", "issn_l": "2047-2501", "issn": ["2047-2501"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "doyens", "jufo-1", "ki-jl-1", "norway-1"], "host_organization": "https://openalex.org/P4310319965", "host_organization_name": "Springer Nature", "host_organization_lineage": ["https://openalex.org/P4310319965"], "host_organization_lineage_names": ["Springer Nature"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Health Information Science and Systems", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4413359336", "doi": "https://doi.org/10.1109/access.2025.3600967", "title": "Advancing Anomaly Detection: Non-Semantic Financial Data Encoding With Large Language Models", "publication_year": 2025, "publication_date": "2025-01-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5048394913", "display_name": "Alexander Bakumenko", "orcid": "https://orcid.org/0000-0001-7212-9573", "observed_orcids": ["https://orcid.org/0000-0001-7212-9573"]}, "institutions": [{"id": "https://openalex.org/I8078737", "display_name": "Clemson University", "ror": "https://ror.org/037s24f05", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I8078737"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Alexander Bakumenko", "raw_affiliation_strings": ["Clemson University, Charleston, SC, USA"], "raw_orcid": "https://orcid.org/0000-0001-7212-9573", "affiliations": [{"raw_affiliation_string": "Clemson University, Charleston, SC, USA", "institution_ids": ["https://openalex.org/I8078737"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5034652116", "display_name": "Kate\u0159ina Hlav\u00e1\u010dkov\u00e1\u2010Schindler", "orcid": "https://orcid.org/0000-0001-6467-3077", "observed_orcids": ["https://orcid.org/0000-0001-6467-3077"]}, "institutions": [{"id": "https://openalex.org/I129774422", "display_name": "University of Vienna", "ror": "https://ror.org/03prydq77", "country_code": "AT", "type": "education", "lineage": ["https://openalex.org/I129774422"]}], "countries": ["AT"], "is_corresponding": false, "raw_author_name": "Kate\u0159ina Hlav\u00e1\u010dkov\u00e1-Schindler", "raw_affiliation_strings": ["Research Group Data Mining and Machine Learning, Faculty of Computer Science, University of Vienna, Vienna, Austria", "Faculty of Computer Science, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria"], "raw_orcid": "https://orcid.org/0000-0001-6467-3077", "affiliations": [{"raw_affiliation_string": "Research Group Data Mining and Machine Learning, Faculty of Computer Science, University of Vienna, Vienna, Austria", "institution_ids": ["https://openalex.org/I129774422"]}, {"raw_affiliation_string": "Faculty of Computer Science, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria", "institution_ids": ["https://openalex.org/I129774422"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5009516958", "display_name": "Claudia Plant", "orcid": "https://orcid.org/0000-0001-5274-8123", "observed_orcids": ["https://orcid.org/0000-0001-5274-8123"]}, "institutions": [{"id": "https://openalex.org/I129774422", "display_name": "University of Vienna", "ror": "https://ror.org/03prydq77", "country_code": "AT", "type": "education", "lineage": ["https://openalex.org/I129774422"]}], "countries": ["AT"], "is_corresponding": false, "raw_author_name": "Claudia Plant", "raw_affiliation_strings": ["Research Group Data Mining and Machine Learning, Faculty of Computer Science, University of Vienna, Vienna, Austria", "Faculty of Computer Science, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria"], "raw_orcid": "https://orcid.org/0000-0001-5274-8123", "affiliations": [{"raw_affiliation_string": "Research Group Data Mining and Machine Learning, Faculty of Computer Science, University of Vienna, Vienna, Austria", "institution_ids": ["https://openalex.org/I129774422"]}, {"raw_affiliation_string": "Faculty of Computer Science, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria", "institution_ids": ["https://openalex.org/I129774422"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5071884087", "display_name": "Nina Hubig", "orcid": "https://orcid.org/0000-0002-8911-7832", "observed_orcids": ["https://orcid.org/0000-0002-8911-7832"]}, "institutions": [{"id": "https://openalex.org/I4403928435", "display_name": "Interdisciplinary Transformation University Austria", "ror": "https://ror.org/03jzk4720", "country_code": "AT", "type": "education", "lineage": ["https://openalex.org/I4403928435"]}], "countries": ["AT"], "is_corresponding": false, "raw_author_name": "Nina C. Hubig", "raw_affiliation_strings": ["IT:U Interdisciplinary Transformation University Austria, Linz, Austria"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "IT:U Interdisciplinary Transformation University Austria, Linz, Austria", "institution_ids": ["https://openalex.org/I4403928435"]}]}], "abstract_inverted_index": {"Detecting": [0], "anomalies": [1], "in": [2, 46, 66, 141, 156, 160, 181], "general": [3], "ledger": [4], "data": [5, 53, 68, 79, 180], "is": [6], "of": [7, 14, 40, 154], "utmost": [8], "importance": [9], "to": [10, 26, 52, 63, 132], "ensure": [11], "the": [12, 98, 139, 152, 182], "trustworthiness": [13], "financial": [15, 67, 88, 161, 183], "records.": [16], "Financial": [17], "audits": [18], "increasingly": [19], "rely": [20], "on": [21, 174], "machine": [22, 43], "learning": [23], "(ML)": [24], "algorithms": [25], "identify": [27], "irregular": [28], "or": [29], "potentially": [30], "fraudulent": [31], "journal": [32, 162], "entries,": [33, 163], "each": [34], "characterized": [35], "by": [36, 144, 165], "a": [37, 60, 145, 171], "varying": [38], "number": [39], "transactions.": [41], "In": [42, 55], "learning,": [44], "heterogeneity": [45], "feature": [47, 167], "dimensions": [48], "adds": [49], "significant": [50], "complexity": [51], "analysis.": [54], "this": [56], "paper,": [57], "we": [58, 90, 102], "introduce": [59], "novel": [61], "approach": [62], "anomaly": [64, 133, 158], "detection": [65, 134, 159], "using": [69, 175], "Large": [70], "Language": [71], "Model": [72], "(LLM)": [73], "embeddings.": [74], "To": [75], "encode": [76], "non-semantic": [77, 179], "categorical": [78], "(i.e.,": [80], "attributes": [81], "lacking": [82], "inherent": [83], "linguistic": [84], "meaning)": [85], "from": [86], "real-world": [87], "records,": [89], "tested": [91], "3": [92], "pretrained": [93], "general-purpose": [94], "sentence-transformer": [95], "models.": [96], "For": [97], "downstream": [99], "classification": [100], "task,": [101], "implemented": [103], "and": [104, 121, 185], "evaluated": [105], "5": [106], "optimized": [107], "ML": [108], "models,": [109], "including": [110], "Logistic": [111], "Regression,": [112], "Random": [113], "Forest,": [114], "Gradient": [115], "Boosting": [116], "Machines,": [117, 120], "Support": [118], "Vector": [119], "Neural": [122], "Networks.": [123], "Our": [124], "experiments": [125], "demonstrate": [126], "that": [127], "LLMs": [128, 155], "contribute": [129], "valuable": [130], "information": [131], "as": [135], "our": [136], "models": [137], "outperform": [138], "baselines,": [140], "selected": [142], "settings": [143], "large": [146], "margin.": [147], "The": [148], "findings": [149], "further": [150], "underscore": [151], "effectiveness": [153], "enhancing": [157], "particularly": [164], "tackling": [166], "sparsity.": [168], "We": [169], "discuss": [170], "promising": [172], "perspective": [173], "SBERT": [176], "embeddings": [177], "for": [178], "context": [184], "beyond.": [186]}, "primary_topic": {"id": "https://openalex.org/T11512", "display_name": "Anomaly Detection Techniques and Applications", "score": 0.9696999788284302, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, "topics": [{"id": "https://openalex.org/T11512", "display_name": "Anomaly Detection Techniques and Applications", "score": 0.9696999788284302, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.010400000028312206, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}, {"id": "https://openalex.org/T11652", "display_name": "Imbalanced Data Classification Techniques", "score": 0.006099999882280827, "subfield": {"id": "https://openalex.org/subfields/1702", "display_name": "Artificial Intelligence"}, "field": {"id": "https://openalex.org/fields/17", "display_name": "Computer Science"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "doi:10.1109/access.2025.3600967", "is_oa": true, "landing_page_url": "https://doi.org/10.1109/access.2025.3600967", "pdf_url": null, "source": {"id": "https://openalex.org/S2485537415", "display_name": "IEEE Access", "issn_l": "2169-3536", "issn": ["2169-3536"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "jufo-1", "ki-jl-1", "norway-1"], "host_organization": "https://openalex.org/P4310319808", "host_organization_name": "Institute of Electrical and Electronics Engineers", "host_organization_lineage": ["https://openalex.org/P4310319808"], "host_organization_lineage_names": ["Institute of Electrical and Electronics Engineers"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "IEEE Access", "raw_type": "journal-article"}, "cited_by_count": 11, "is_retracted": false}], "group_by": []}