{"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 \"chain of thought\" OR stemmed \"language model reasoning\" OR stemmed \"reasoning model\" OR stemmed \"test time compute\" OR stemmed \"test time scaling\") AND (stemmed \"language model\" OR stemmed \"large language model\" OR stemmed \"vision language model\"))\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": "\"chain of thought\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"language model reasoning\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"reasoning model\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"test time compute\"", "operator": "has"}, {"column_id": "title_and_abstract.search", "value": "\"test time scaling\"", "operator": "has"}]}, {"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": "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:%22chain of thought%22|%22language model reasoning%22|%22reasoning model%22|%22test time compute%22|%22test time scaling%22,title_and_abstract.search:%22language model%22|%22large language model%22|%22vision language model%22,type:article|preprint|review&sample=2000&seed=42&per_page=100&page=1"}, "cost_usd": 0.001}, "results": [{"id": "https://openalex.org/W4415070848", "doi": "https://doi.org/10.48550/arxiv.2506.13300", "title": "Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models", "publication_year": 2025, "publication_date": "2025-06-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100758169", "display_name": "Bo Hu Li", "orcid": "https://orcid.org/0000-0001-5980-4861", "observed_orcids": ["https://orcid.org/0000-0001-5980-4861"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Bo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5034706235", "display_name": "Chengben Xu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Chengben", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030057663", "display_name": "Wufeng Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Wufeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"This": [0, 76], "paper": [1], "presents": [2], "Seewo's": [3], "systems": [4], "for": [5, 44, 51, 98, 106], "both": [6], "tracks": [7], "of": [8, 96, 104, 115], "the": [9, 82, 87, 113], "Multilingual": [10], "Conversational": [11], "Speech": [12], "Language": [13], "Model": [14], "Challenge": [15], "(MLC-SLM),": [16], "addressing": [17], "automatic": [18], "speech": [19, 41], "recognition": [20], "(ASR)": [21], "and": [22, 38, 62, 101], "speaker": [23], "diarization": [24], "with": [25, 65], "ASR": [26], "(SD-ASR).": [27], "We": [28], "introduce": [29], "a": [30, 94, 102], "multi-stage": [31], "training": [32], "pipeline": [33], "that": [34], "explicitly": [35], "enhances": [36], "reasoning": [37], "self-correction": [39, 72], "in": [40], "language": [42], "models": [43], "ASR.": [45], "Our": [46], "approach": [47, 77], "combines": [48], "curriculum": [49], "learning": [50], "progressive": [52], "capability": [53], "acquisition,": [54], "Chain-of-Thought": [55], "data": [56], "augmentation": [57], "to": [58, 69], "foster": [59], "intermediate": [60], "reflection,": [61], "Reinforcement": [63], "Learning": [64], "Verifiable": [66], "Rewards": [67], "(RLVR)": [68], "further": [70], "refine": [71], "through": [73], "reward-driven": [74], "optimization.": [75], "achieves": [78], "substantial": [79], "improvements": [80], "over": [81], "official": [83], "challenge": [84, 119], "baselines.": [85], "On": [86], "evaluation": [88], "set,": [89], "our": [90], "best": [91], "system": [92], "attains": [93], "WER/CER": [95], "11.57%": [97], "Track": [99, 107], "1": [100], "tcpWER/tcpCER": [103], "17.67%": [105], "2.": [108], "Comprehensive": [109], "ablation": [110], "studies": [111], "demonstrate": [112], "effectiveness": [114], "each": [116], "component": [117], "under": [118], "constraints.": [120]}, "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/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"}}, {"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "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:2506.13300", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.13300", "pdf_url": "https://arxiv.org/pdf/2506.13300", "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/W4407424722", "doi": "https://doi.org/10.48550/arxiv.2502.07374", "title": "LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!", "publication_year": 2025, "publication_date": "2025-02-11", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5016324529", "display_name": "Dacheng Li", "orcid": "https://orcid.org/0009-0005-1895-1933", "observed_orcids": ["https://orcid.org/0009-0005-1895-1933"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Li, Dacheng", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039788110", "display_name": "Shiyi Cao", "orcid": "https://orcid.org/0000-0002-1953-7751", "observed_orcids": ["https://orcid.org/0000-0002-1953-7751", "https://orcid.org/0009-0005-6834-375X"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Cao, Shiyi", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5095886747", "display_name": "Tyler Griggs", "orcid": "https://orcid.org/0009-0006-4655-0229", "observed_orcids": ["https://orcid.org/0009-0006-4655-0229"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Griggs, Tyler", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5023175954", "display_name": "Shu Liu", "orcid": "https://orcid.org/0000-0002-9812-7821", "observed_orcids": ["https://orcid.org/0000-0002-9812-7821"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Liu, Shu", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042410262", "display_name": "Xiangxi Mo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Mo, Xiangxi", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Tang, Eric", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tang, Eric", "raw_affiliation_strings": ["Anyscale"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Anyscale", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Hegde, Sumanth", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hegde, Sumanth", "raw_affiliation_strings": ["Anyscale"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Anyscale", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Hakhamaneshi, Kourosh", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hakhamaneshi, Kourosh", "raw_affiliation_strings": ["Anyscale"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Anyscale", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5022259826", "display_name": "Shishir G. Patil", "orcid": "https://orcid.org/0000-0001-6835-388X", "observed_orcids": ["https://orcid.org/0000-0001-6835-388X"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Patil, Shishir G.", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005554337", "display_name": "Matei Zaharia", "orcid": "https://orcid.org/0000-0002-7547-7204", "observed_orcids": ["https://orcid.org/0000-0002-7547-7204"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Zaharia, Matei", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5072427753", "display_name": "Joseph E. Gonzalez", "orcid": "https://orcid.org/0000-0003-2921-956X", "observed_orcids": ["https://orcid.org/0000-0003-2921-956X"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Gonzalez, Joseph E.", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5041920173", "display_name": "Ion Gabriel Stoica", "orcid": "https://orcid.org/0000-0002-5373-0088", "observed_orcids": ["https://orcid.org/0000-0002-5373-0088"]}, "institutions": [{"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Stoica, Ion", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , University of California , Berkeley"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , University of California , Berkeley", "institution_ids": ["https://openalex.org/I95457486"]}]}], "abstract_inverted_index": {"Large": [0, 41], "reasoning": [1, 6, 50, 126, 142, 166, 205, 220], "models": [2], "(LRMs)": [3], "tackle": [4], "complex": [5], "problems": [7], "by": [8], "following": [9], "long": [10, 64], "chain-of-thoughts": [11], "(Long": [12], "CoT)": [13], "that": [14, 39, 109, 153], "incorporate": [15], "reflection,": [16], "backtracking,": [17], "and": [18, 24, 56, 80, 89, 103, 209], "self-validation.": [19], "However,": [20], "the": [21, 68, 96, 110, 118, 122, 158, 216, 224], "training": [22, 66, 136, 191, 215], "techniques": [23], "data": [25], "requirements": [26], "to": [27, 95, 117, 190, 203], "elicit": [28, 204], "Long": [29, 48, 113, 159, 177], "CoT": [30, 49, 65, 114, 178], "remain": [31], "poorly": [32], "understood.": [33], "In": [34, 149], "this": [35], "work,": [36], "we": [37, 107], "find": [38, 108], "a": [40, 75, 173], "Language": [42], "model": [43, 70, 174], "(LLM)": [44], "can": [45], "effectively": [46], "learn": [47], "through": [51], "data-efficient": [52], "supervised": [53], "fine-tuning": [54], "(SFT)": [55], "parameter-efficient": [57], "low-rank": [58], "adaptation": [59], "(LoRA).": [60], "With": [61], "just": [62], "17k": [63], "samples,": [67], "Qwen2.5-32B-Instruct": [69], "achieves": [71, 184], "significant": [72], "improvements": [73], "on": [74, 86, 92, 137, 147, 176], "wide": [76], "range": [77], "of": [78, 101, 112, 124, 201, 219, 227], "math": [79], "coding": [81], "benchmarks,": [82], "including": [83], "56.7%": [84], "(+40.0%)": [85], "AIME": [87], "2024": [88], "57.0%": [90], "(+8.1%)": [91], "LiveCodeBench,": [93], "competitive": [94], "proprietary": [97], "o1-preview": [98], "model's": [99], "score": [100], "44.6%": [102], "59.1%.": [104], "More": [105], "importantly,": [106], "structure": [111], "is": [115, 223], "critical": [116], "learning": [119], "process,": [120], "whereas": [121], "content": [123], "individual": [125], "steps": [127], "has": [128], "minimal": [129], "impact.": [130], "Perturbations": [131], "affecting": [132], "content,": [133], "such": [134, 161], "as": [135, 162], "incorrect": [138, 181], "samples": [139, 179], "or": [140, 164], "removing": [141], "keywords,": [143], "have": [144], "little": [145], "impact": [146], "performance.": [148], "contrast,": [150], "structural": [151], "modifications": [152], "disrupt": [154], "logical": [155], "consistency": [156], "in": [157, 207], "CoT,": [160], "shuffling": [163], "deleting": [165], "steps,": [167], "significantly": [168], "degrade": [169], "accuracy.": [170], "For": [171], "example,": [172], "trained": [175], "with": [180, 192], "answers": [182], "still": [183], "only": [185], "3.2%": [186], "lower": [187], "accuracy": [188], "compared": [189], "fully": [193], "correct": [194], "samples.": [195], "These": [196], "insights": [197], "deepen": [198], "our": [199, 228], "understanding": [200], "how": [202], "capabilities": [206], "LLMs": [208], "highlight": [210], "key": [211], "considerations": [212], "for": [213], "efficiently": [214], "next": [217], "generation": [218], "models.": [221], "This": [222], "academic": [225], "paper": [226], "previous": [229], "released": [230], "Sky-T1-32B-Preview": [231], "model.": [232], "Codes": [233], "are": [234], "available": [235], "at": [236], "https://github.com/NovaSky-AI/SkyThought.": [237]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7792999744415283, "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": 0.7792999744415283, "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": 0.0348999984562397, "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": 0.03020000085234642, "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:2502.07374", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.07374", "pdf_url": "https://arxiv.org/pdf/2502.07374", "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/W4412127082", "doi": "https://doi.org/10.2139/ssrn.5333028", "title": "Can Memory-Augmented Large Language Model Agents Help Journalism in News Interpretation and Cognitive Framing Across Diverse Audiences?", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5117935403", "display_name": "Leyi Ouyang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I101479585", "display_name": "South China Agricultural University", "ror": "https://ror.org/05v9jqt67", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I101479585"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Leyi Ouyang", "raw_affiliation_strings": ["South China Agriculture University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "South China Agriculture University", "institution_ids": ["https://openalex.org/I101479585"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.28610000014305115, "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": 0.28610000014305115, "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/T10133", "display_name": "Media Studies and Communication", "score": 0.17749999463558197, "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/T13629", "display_name": "Text Readability and Simplification", "score": 0.07779999822378159, "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.5333028", "is_oa": true, "landing_page_url": "https://doi.org/10.2139/ssrn.5333028", "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/W4414536410", "doi": "https://doi.org/10.48550/arxiv.2508.13037", "title": "Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction", "publication_year": 2025, "publication_date": "2025-08-18", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073294147", "display_name": "X. Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xinhe", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5029321864", "display_name": "Jiajun Liu", "orcid": "https://orcid.org/0000-0002-7871-0518", "observed_orcids": ["https://orcid.org/0000-0002-7871-0518"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Jiajun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100396091", "display_name": "Peng Wang", "orcid": "https://orcid.org/0000-0002-8745-320X", "observed_orcids": ["https://orcid.org/0000-0002-8745-320X", "https://orcid.org/0000-0001-5876-4650"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Peng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Recent": [0], "studies": [1], "have": [2, 9], "demonstrated": [3], "that": [4, 175, 225], "Large": [5], "Language": [6, 31], "Models": [7, 32], "(LLMs)": [8], "strong": [10], "mathematical": [11, 104, 214], "reasoning": [12, 28, 59, 105, 114, 215], "abilities": [13], "but": [14], "rely": [15], "on": [16, 63, 99, 131, 231], "hundreds": [17], "of": [18, 20, 26, 43, 91, 115, 188, 217], "billions": [19], "parameters.": [21], "To": [22], "tackle": [23], "the": [24, 100, 111, 132, 154, 172, 183, 186, 200, 213, 232, 238, 250], "challenge": [25], "poor": [27], "in": [29, 185], "Small": [30], "(SLMs),": [33], "existing": [34], "methods": [35], "typically": [36], "leverage": [37], "LLMs": [38], "to": [39, 53, 121, 147, 177, 181, 204], "generate": [40], "massive": [41], "amounts": [42], "data": [44], "for": [45, 103, 144], "cramming": [46], "training.": [47], "In": [48], "psychology,": [49], "they": [50], "are": [51, 197], "akin": [52], "System": [54, 72, 149], "1": [55], "thinking,": [56, 74, 92, 151], "which": [57, 140], "resolves": [58], "problems": [60], "rapidly": [61], "based": [62, 98], "experience": [64], "and": [65, 80, 113, 158, 190, 199, 246], "intuition.": [66], "However,": [67], "human": [68], "learning": [69], "also": [70], "requires": [71], "2": [73, 150], "where": [75, 235], "knowledge": [76, 167, 176], "is": [77], "first": [78], "acquired": [79], "then": [81], "reinforced": [82], "through": [83, 219], "practice.": [84], "Inspired": [85], "by": [86, 241], "such": [87], "two": [88], "distinct": [89], "modes": [90], "we": [93, 109, 126, 152, 192], "propose": [94], "a": [95, 128], "novel": [96], "method": [97, 240], "multi-LoRA": [101], "Interaction": [102], "Distillation": [106], "(LoRID).": [107], "First,": [108], "input": [110], "question": [112], "each": [116], "sample": [117], "into": [118], "an": [119, 136], "LLM": [120], "create": [122], "knowledge-enhanced": [123], "datasets.": [124], "Subsequently,": [125], "train": [127, 153], "LoRA": [129], "block": [130], "student": [133], "model": [134], "as": [135], "Intuitive": [137], "Reasoner": [138, 160], "(IR),": [139], "directly": [141], "generates": [142], "Chain-of-Thoughts": [143], "problem-solving.": [145], "Then,": [146], "imitate": [148], "Knowledge": [155], "Generator": [156], "(KG)": [157], "Deep": [159], "(DR),": [161], "respectively.": [162, 254], "The": [163], "former": [164], "outputs": [165, 196], "only": [166], "after": [168], "receiving": [169], "problems,": [170], "while": [171], "latter": [173], "uses": [174], "perform": [178], "reasoning.": [179], "Finally,": [180], "address": [182], "randomness": [184], "generation": [187], "IR": [189], "DR,": [191], "evaluate": [193], "whether": [194], "their": [195], "consistent,": [198], "inference": [201], "process": [202], "needs": [203], "be": [205], "iterated": [206], "if": [207], "not.": [208], "This": [209], "step": [210], "can": [211], "enhance": [212], "ability": [216], "SLMs": [218], "mutual": [220], "feedback.": [221], "Experimental": [222], "results": [223], "show": [224], "LoRID": [226], "achieves": [227], "state-of-the-art": [228], "performance,": [229], "especially": [230], "GSM8K": [233], "dataset,": [234], "it": [236], "outperforms": [237], "second-best": [239], "2.3%,": [242], "16.1%,": [243], "2.4%,": [244], "12.3%,": [245], "1.8%": [247], "accuracy": [248], "across": [249], "five": [251], "base": [252], "models,": [253]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.600600004196167, "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": 0.600600004196167, "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": 0.06790000200271606, "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/T12522", "display_name": "Mathematics Education and Pedagogy", "score": 0.05180000141263008, "subfield": {"id": "https://openalex.org/subfields/2604", "display_name": "Applied Mathematics"}, "field": {"id": "https://openalex.org/fields/26", "display_name": "Mathematics"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2508.13037", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2508.13037", "pdf_url": "https://arxiv.org/pdf/2508.13037", "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/W4417200905", "doi": "https://doi.org/10.48550/arxiv.2511.12309", "title": "Optimal Self-Consistency for Efficient Reasoning with Large Language Models", "publication_year": 2025, "publication_date": "2025-11-15", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Feng, Austin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Feng, Austin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Alonso, Marius", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Alonso, Marius", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5093123204", "display_name": "Ambroise Odonnat", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Odonnat, Ambroise", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Feofanov, Vasilii", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Feofanov, Vasilii", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Redko, Ievgen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Redko, Ievgen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Self-consistency": [0], "(SC)": [1], "is": [2, 53, 184], "a": [3, 24, 42, 66, 128], "widely": [4], "used": [5], "test-time": [6], "inference": [7], "technique": [8], "for": [9, 107, 116], "improving": [10], "performance": [11], "in": [12, 171], "chain-of-thought": [13], "reasoning.": [14], "It": [15], "consists": [16], "of": [17, 70, 85, 131, 168, 173, 193], "generating": [18], "multiple": [19], "responses,": [20], "or": [21, 45], "``samples\",": [22], "from": [23], "large": [25], "language": [26], "model": [27], "(LLM)": [28], "and": [29, 63, 73, 89, 96, 101, 111, 118, 160, 188], "selecting": [30], "the": [31, 81, 113, 166], "most": [32], "frequent": [33], "answer.": [34], "This": [35], "procedure": [36], "can": [37, 189, 197], "naturally": [38], "be": [39, 198], "viewed": [40], "as": [41], "majority": [43], "vote": [44], "empirical": [46], "mode": [47, 94], "estimation.": [48], "Despite": [49], "its": [50, 90], "effectiveness,": [51], "self-consistency": [52, 108, 132, 203], "prohibitively": [54], "expensive": [55], "at": [56], "scale": [57], "when": [58], "naively": [59], "applied": [60, 200], "to": [61, 137, 177, 201], "datasets,": [62, 110], "it": [64, 196], "lacks": [65], "unified": [67], "theoretical": [68], "understanding": [69], "sample": [71, 114, 143], "efficiency": [72, 115], "scaling": [74, 87, 106], "behavior.": [75], "In": [76, 175], "this": [77], "paper,": [78], "we": [79, 125, 180], "provide": [80], "first": [82], "comprehensive": [83], "analysis": [84], "SC's": [86], "behavior": [88], "variants,": [91, 179], "drawing": [92], "on": [93, 155], "estimation": [95], "voting": [97], "theory.": [98], "We": [99], "derive": [100], "empirically": [102], "validate": [103], "power": [104], "law": [105], "across": [109], "analyze": [112], "fixed-allocation": [117], "dynamic-allocation": [119, 161], "sampling": [120], "schemes.": [121], "From": [122], "these": [123], "insights,": [124], "introduce": [126], "Blend-ASC,": [127], "novel": [129], "variant": [130], "that": [133, 182], "dynamically": [134], "allocates": [135], "samples": [136, 151], "questions": [138], "during": [139], "inference,": [140], "achieving": [141], "state-of-the-art": [142], "efficiency.": [144, 174], "Our": [145], "approach": [146, 170], "uses": [147], "4.8": [148], "times": [149], "fewer": [150], "than": [152], "vanilla": [153], "SC": [154, 162], "average,": [156], "outperforming": [157], "both": [158], "fixed-": [159], "baselines,": [163], "thereby": [164], "demonstrating": [165], "superiority": [167], "our": [169], "terms": [172], "contrast": [176], "existing": [178], "note": [181], "Blend-ASC": [183], "hyperparameter-free,": [185], "supports": [186], "batching,": [187], "fit": [190], "any": [191, 202], "budget": [192], "samples,": [194], "ensuring": [195], "easily": [199], "application.": [204]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.86080002784729, "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": 0.86080002784729, "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": 0.05700000002980232, "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/T12072", "display_name": "Machine Learning and Algorithms", "score": 0.013799999840557575, "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:2511.12309", "is_oa": true, "landing_page_url": "https://arxiv.org/abs/2511.12309", "pdf_url": "https://arxiv.org/pdf/2511.12309", "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": 1, "is_retracted": false}, {"id": "https://openalex.org/W4409877648", "doi": "https://doi.org/10.1007/s11432-024-4404-4", "title": "Autonomous embodied navigation task generation from natural language dialogues", "publication_year": 2025, "publication_date": "2025-04-25", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101434141", "display_name": "Haifeng Xu", "orcid": "https://orcid.org/0000-0001-6371-4906", "observed_orcids": ["https://orcid.org/0000-0001-6371-4906"]}, "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": "Haifeng Xu", "raw_affiliation_strings": ["Department of Automation, Tsinghua University, Beijing, 100084, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, Tsinghua University, Beijing, 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101581292", "display_name": "Yongchang Li", "orcid": "https://orcid.org/0000-0003-4589-0062", "observed_orcids": ["https://orcid.org/0000-0003-4589-0062"]}, "institutions": [{"id": "https://openalex.org/I18452120", "display_name": "Yantai University", "ror": "https://ror.org/01rp41m56", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I18452120"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yongchang Li", "raw_affiliation_strings": ["School of Physics and Electronic Information, Yantai University, Yantai, 264005, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Physics and Electronic Information, Yantai University, Yantai, 264005, China", "institution_ids": ["https://openalex.org/I18452120"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5064304208", "display_name": "Lei Ma", "orcid": "https://orcid.org/0000-0002-0906-3978", "observed_orcids": ["https://orcid.org/0000-0002-0906-3978"]}, "institutions": [{"id": "https://openalex.org/I67001856", "display_name": "Shanghai Institute of Technology", "ror": "https://ror.org/00fjzqj15", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I67001856"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lumeng Ma", "raw_affiliation_strings": ["School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, 201418, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, 201418, China", "institution_ids": ["https://openalex.org/I67001856"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103714205", "display_name": "Chunwen Li", "orcid": null, "observed_orcids": []}, "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": "Chunwen Li", "raw_affiliation_strings": ["Department of Automation, Tsinghua University, Beijing, 100084, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Automation, Tsinghua University, Beijing, 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5037709138", "display_name": "Yanzhi Dong", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I18452120", "display_name": "Yantai University", "ror": "https://ror.org/01rp41m56", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I18452120"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yanzhi Dong", "raw_affiliation_strings": ["School of Physics and Electronic Information, Yantai University, Yantai, 264005, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Physics and Electronic Information, Yantai University, Yantai, 264005, China", "institution_ids": ["https://openalex.org/I18452120"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5013721700", "display_name": "Xiaohu Yuan", "orcid": "https://orcid.org/0009-0008-4239-2889", "observed_orcids": ["https://orcid.org/0009-0008-4239-2889"]}, "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": "Xiaohu Yuan", "raw_affiliation_strings": ["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101678494", "display_name": "Huaping Liu", "orcid": "https://orcid.org/0000-0001-7017-4127", "observed_orcids": ["https://orcid.org/0000-0001-7017-4127"]}, "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": "Huaping Liu", "raw_affiliation_strings": ["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T12031", "display_name": "Speech and dialogue systems", "score": 0.9589999914169312, "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": 0.9589999914169312, "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/T10653", "display_name": "Robot Manipulation and Learning", "score": 0.016200000420212746, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems 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/T10709", "display_name": "Social Robot Interaction and HRI", "score": 0.006399999838322401, "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"}}], "primary_location": {"id": "doi:10.1007/s11432-024-4404-4", "is_oa": false, "landing_page_url": "https://doi.org/10.1007/s11432-024-4404-4", "pdf_url": null, "source": {"id": "https://openalex.org/S4210218743", "display_name": "Science China Information Sciences", "issn_l": "1869-1919", "issn": ["1869-1919", "1674-733X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-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": "Science China Information Sciences", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4416038690", "doi": "https://doi.org/10.48550/arxiv.2503.10177", "title": "PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning", "publication_year": 2025, "publication_date": "2025-03-13", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5016236429", "display_name": "Yirong Sun", "orcid": "https://orcid.org/0000-0002-0617-5595", "observed_orcids": ["https://orcid.org/0000-0002-0617-5595"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Yirong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5114488762", "display_name": "Yanjun Chen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Yanjun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0], "propose": [1], "PRISM,": [2], "a": [3, 32, 144], "novel": [4], "framework": [5], "designed": [6], "to": [7, 38, 58, 75, 88], "overcome": [8], "the": [9, 64], "limitations": [10], "of": [11, 81], "2D-based": [12], "Preference-Based": [13], "Reinforcement": [14], "Learning": [15], "(PBRL)": [16], "by": [17], "unifying": [18], "3D": [19, 33, 82, 135], "point": [20], "cloud": [21], "modeling": [22], "and": [23, 41, 47, 84, 98, 114, 127], "future-aware": [24], "preference": [25, 50, 71, 92, 140], "refinement.": [26], "At": [27], "its": [28], "core,": [29], "PRISM": [30, 53, 142], "adopts": [31], "Point": [34], "Cloud-Language": [35], "Model": [36], "(3D-PC-LLM)": [37], "mitigate": [39], "occlusion": [40], "viewpoint": [42], "biases,": [43], "ensuring": [44], "more": [45], "stable": [46], "spatially": [48], "consistent": [49], "signals.": [51], "Additionally,": [52], "leverages": [54], "Chain-of-Thought": [55], "(CoT)": [56], "reasoning": [57, 86], "incorporate": [59], "long-horizon": [60], "considerations,": [61], "thereby": [62], "preventing": [63], "short-sighted": [65], "feedback": [66], "often": [67], "seen": [68], "in": [69, 91], "static": [70], "comparisons.": [72], "In": [73], "contrast": [74], "conventional": [76], "PBRL": [77], "techniques,": [78], "this": [79], "integration": [80], "perception": [83], "future-oriented": [85], "leads": [87], "significant": [89], "gains": [90], "agreement": [93], "rates,": [94], "faster": [95], "policy": [96], "convergence,": [97], "robust": [99], "generalization": [100], "across": [101], "unseen": [102], "robotic": [103, 112], "environments.": [104], "Our": [105], "empirical": [106], "results,": [107], "spanning": [108], "tasks": [109], "such": [110], "as": [111], "manipulation": [113], "autonomous": [115], "navigation,": [116], "highlight": [117], "PRISM's": [118], "potential": [119], "for": [120, 147], "real-world": [121], "applications": [122], "where": [123], "precise": [124], "spatial": [125], "understanding": [126], "reliable": [128], "long-term": [129], "decision-making": [130], "are": [131], "critical.": [132], "By": [133], "bridging": [134], "geometric": [136], "awareness": [137], "with": [138], "CoT-driven": [139], "modeling,": [141], "establishes": [143], "comprehensive": [145], "foundation": [146], "scalable,": [148], "human-aligned": [149], "reinforcement": [150], "learning.": [151]}, "primary_topic": {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "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/T10462", "display_name": "Reinforcement Learning in Robotics", "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/T10653", "display_name": "Robot Manipulation and Learning", "score": 0.0013000000035390258, "subfield": {"id": "https://openalex.org/subfields/2207", "display_name": "Control and Systems 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/T10719", "display_name": "3D Shape Modeling and Analysis", "score": 0.0, "subfield": {"id": "https://openalex.org/subfields/2206", "display_name": "Computational Mechanics"}, "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:2503.10177", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.10177", "pdf_url": "https://arxiv.org/pdf/2503.10177", "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/W4415193096", "doi": "https://doi.org/10.48550/arxiv.2508.06153", "title": "SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs", "publication_year": 2025, "publication_date": "2025-08-08", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Wu, Zhengxian", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wu, Zhengxian", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Wen, Juan", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wen, Juan", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Peng, Wanli", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Peng, Wanli", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Chang, Haowei", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chang, Haowei", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100678775", "display_name": "Yinghan Zhou", "orcid": "https://orcid.org/0009-0006-6366-9838", "observed_orcids": ["https://orcid.org/0009-0006-6366-9838", "https://orcid.org/0009-0008-3467-8000"]}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhou, Yinghan", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Xue, Yiming", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I52158045", "display_name": "China Agricultural University", "ror": "https://ror.org/04v3ywz14", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I52158045"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xue, Yiming", "raw_affiliation_strings": ["College of Information and Electrical Engineering , China Agricultural University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Information and Electrical Engineering , China Agricultural University", "institution_ids": ["https://openalex.org/I52158045"]}]}], "abstract_inverted_index": {"Customized": [0], "Large": [1], "Language": [2], "Model": [3], "(LLM)": [4], "agents": [5], "face": [6], "a": [7, 52, 103], "critical": [8], "security": [9], "threat": [10], "from": [11], "black-box": [12, 199], "instruction": [13, 59], "backdoors,": [14], "where": [15, 86], "malicious": [16], "behaviors": [17], "are": [18], "covertly": [19], "injected": [20], "through": [21], "hidden": [22], "system": [23], "instructions.": [24], "Although": [25], "existing": [26], "prompt-based": [27], "defenses": [28], "can": [29], "often": [30], "detect": [31], "poisoned": [32], "inputs,": [33], "they": [34], "generally": [35], "fail": [36], "to": [37, 130, 166, 189, 194], "recover": [38], "correct": [39], "outputs": [40], "once": [41], "the": [42, 74, 119, 122, 128, 140, 149, 154, 184], "backdoor": [43, 71], "is": [44], "activated.": [45], "In": [46], "this": [47], "paper,": [48], "we": [49, 101], "first": [50], "conduct": [51], "mechanistic": [53], "analysis": [54], "of": [55], "LLM": [56], "behavior": [57], "under": [58], "backdoors": [60, 113], "and": [61, 77, 81, 107, 134, 162, 174, 196], "reveal": [62], "two": [63], "pivotal": [64], "phenomena:": [65], "(1)": [66], "cognitive": [67, 120], "override,": [68, 121], "in": [69, 114], "which": [70], "triggers": [72, 87], "dominate": [73], "reasoning": [75], "process": [76], "suppress": [78], "task-relevant": [79, 132], "context,": [80], "(2)": [82], "abnormal": [83, 151], "semantic": [84, 91, 152, 160], "correlation,": [85, 153], "establish": [88], "excessively": [89], "strong": [90], "associations": [92], "with": [93], "attacker-specified": [94], "target": [95], "labels.": [96], "Based": [97], "on": [98], "these": [99], "insights,": [100], "propose": [102], "$\\textbf{S}$oft": [104], "$\\textbf{L}$abel": [105], "mechanism": [106, 157], "key-extraction-guided": [108, 123], "CoT-based": [109], "defense": [110], "against": [111], "$\\textbf{I}$nstruction": [112], "A$\\textbf{P}$Is": [115], "(SLIP).": [116], "To": [117, 147], "counteract": [118], "Chain-of-Thought": [124], "(KCOT)": [125], "explicitly": [126], "guides": [127], "model": [129], "extract": [131], "keywords": [133, 173], "phrases": [135, 169, 175], "rather": [136], "than": [137], "only": [138], "considering": [139], "single": [141], "trigger": [142], "or": [143], "overall": [144], "text": [145], "semantics.": [146], "neutralize": [148], "trigger's": [150], "soft": [155], "label": [156], "(SLM)": [158], "quantifies": [159], "correlations": [161], "employs": [163], "statistical": [164], "clustering": [165], "filter": [167], "anomalous": [168], "before": [170], "aggregating": [171], "reliable": [172], "for": [176], "prediction.": [177], "Extensive": [178], "experiments": [179], "show": [180], "that": [181], "SLIP": [182], "reduces": [183], "average": [185], "attack": [186], "success": [187], "rate": [188], "25.13$\\%$,": [190], "improves": [191], "clean": [192], "accuracy": [193], "87.15$\\%$,": [195], "outperforms": [197], "state-of-the-art": [198], "defenses.": [200]}, "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/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:2508.06153", "is_oa": true, "landing_page_url": "https://arxiv.org/abs/2508.06153", "pdf_url": "https://arxiv.org/pdf/2508.06153", "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/W7106690462", "doi": "https://doi.org/10.48550/arxiv.2511.18423", "title": "General Agentic Memory Via Deep Research", "publication_year": 2025, "publication_date": "2025-11-23", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yan, B. Y.", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yan, B. Y.", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Li, Chaofan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Chaofan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Qian, Hongjin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qian, Hongjin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Lu, Shuqi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lu, Shuqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Liu, Zheng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Zheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Memory": [0], "is": [1, 19], "critical": [2], "for": [3, 56, 114], "AI": [4], "agents,": [5], "yet": [6], "the": [7, 42, 69, 80, 112, 120, 130], "widely-adopted": [8], "static": [9], "memory,": [10, 93], "aiming": [11], "to": [12, 22, 127], "create": [13], "readily": [14], "available": [15], "memory": [16, 38, 67, 170], "in": [17], "advance,": [18], "inevitably": [20], "subject": [21], "severe": [23], "information": [24, 89, 98, 110], "loss.": [25], "To": [26, 72], "address": [27], "this": [28, 73], "limitation,": [29], "we": [30, 155], "propose": [31], "a": [32, 77, 91, 100], "novel": [33], "framework": [34], "called": [35], "\\textbf{general": [36], "agentic": [37, 131], "(GAM)}.": [39], "GAM": [40, 75, 126, 158], "follows": [41], "principle": [43], "of": [44, 136], "\"\\textbf{just-in": [45], "time": [46], "(JIT)": [47], "compilation}\"": [48], "where": [49], "it": [50], "focuses": [51], "on": [52, 162], "creating": [53], "optimized": [54], "contexts": [55], "its": [57, 115], "client": [58], "at": [59], "runtime": [60], "while": [61, 94, 142], "keeping": [62], "only": [63], "simple": [64], "but": [65], "useful": [66, 109], "during": [68], "offline": [70], "stage.": [71], "end,": [74], "employs": [76], "duo-design": [78], "with": [79], "following": [81], "components.": [82], "1)": [83], "\\textbf{Memorizer},": [84], "which": [85, 105], "highlights": [86], "key": [87], "historical": [88, 97], "using": [90], "lightweight": [92], "maintaining": [95], "complete": [96], "within": [99], "universal": [101], "page-store.": [102], "2)": [103], "\\textbf{Researcher},": [104], "retrieves": [106], "and": [107, 133], "integrates": [108], "from": [111], "page-store": [113], "online": [116], "request": [117], "guided": [118], "by": [119], "pre-constructed": [121], "memory.": [122], "This": [123], "design": [124], "allows": [125], "effectively": [128], "leverage": [129], "capabilities": [132], "test-time": [134], "scalability": [135], "frontier": [137], "large": [138], "language": [139], "models": [140], "(LLMs),": [141], "also": [143], "facilitating": [144], "end-to-end": [145], "performance": [146], "optimization": [147], "through": [148], "reinforcement": [149], "learning.": [150], "In": [151], "our": [152], "experimental": [153], "study,": [154], "demonstrate": [156], "that": [157], "achieves": [159], "substantial": [160], "improvement": [161], "various": [163], "memory-grounded": [164], "task": [165], "completion": [166], "scenarios": [167], "against": [168], "existing": [169], "systems.": [171]}, "primary_topic": {"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.5473999977111816, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.5473999977111816, "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": 0.09130000323057175, "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/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.06759999692440033, "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:2511.18423", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.18423", "pdf_url": "https://arxiv.org/pdf/2511.18423", "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/W4415947120", "doi": "https://doi.org/10.48550/arxiv.2510.09211", "title": "DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction", "publication_year": 2025, "publication_date": "2025-10-10", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Li, Yiqi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Yiqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120274838", "display_name": "Yusheng Liao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liao, Yusheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100457678", "display_name": "Zhe Chen", "orcid": "https://orcid.org/0000-0002-2919-4481", "observed_orcids": ["https://orcid.org/0000-0002-2919-4481", "https://orcid.org/0009-0003-7056-0601", "https://orcid.org/0009-0004-1735-7097", "https://orcid.org/0009-0005-3379-0613", "https://orcid.org/0009-0006-5492-3013", "https://orcid.org/0009-0007-5089-0848", "https://orcid.org/0009-0008-3316-5334", "https://orcid.org/0009-0008-5387-0655", "https://orcid.org/0000-0002-0088-7591", "https://orcid.org/0000-0003-2590-0307"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Zhe", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100645710", "display_name": "Yanfeng Wang", "orcid": "https://orcid.org/0000-0002-8623-1111", "observed_orcids": ["https://orcid.org/0000-0002-8623-1111", "https://orcid.org/0000-0002-3196-2347"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yanfeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100445204", "display_name": "Yu Wang", "orcid": "https://orcid.org/0000-0002-3883-5578", "observed_orcids": ["https://orcid.org/0000-0002-3883-5578", "https://orcid.org/0000-0002-7371-8238"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"When": [0], "performing": [1], "reasoning": [2, 18, 101], "tasks": [3], "with": [4], "user-specific": [5], "requirements,": [6], "such": [7], "as": [8], "strict": [9], "output": [10, 92], "formats,": [11], "large": [12], "language": [13, 55, 77], "models": [14, 56], "(LLMs)": [15], "often": [16], "prioritize": [17], "over": [19, 164], "adherence": [20], "to": [21, 29, 35, 58, 74, 83, 89, 108, 129], "detailed": [22], "instructions.": [23], "Fine-tuning": [24], "LLMs": [25, 73], "on": [26], "supervised": [27], "datasets": [28, 118], "address": [30], "this": [31], "is": [32], "impractical": [33], "due": [34], "high": [36], "computational": [37], "costs": [38], "and": [39, 85, 100, 123, 149, 157], "limited": [40], "parameter": [41], "access.": [42], "To": [43], "tackle": [44], "this,": [45], "we": [46], "propose": [47], "DICE,": [48], "a": [49, 120, 126], "lightweight": [50], "framework": [51, 95], "that": [52, 142], "guides": [53], "small": [54], "(SLMs)": [57], "refine": [59, 86], "LLMs'": [60, 97], "outputs": [61, 88, 106, 135, 154], "through": [62], "chain-of-thought": [63], "(CoT)": [64], "correction.": [65], "DICE": [66, 112, 143], "decouples": [67], "the": [68, 105, 145], "process": [69], "by": [70, 155], "first": [71, 113], "prompting": [72], "generate": [75], "natural": [76], "responses,": [78], "then": [79], "using": [80], "trained": [81], "SLMs": [82, 131], "analyze": [84], "these": [87], "meet": [90], "structured": [91, 115, 134], "specifications.": [93], "This": [94], "preserves": [96], "broad": [98], "knowledge": [99], "capabilities": [102], "while": [103], "ensuring": [104], "conform": [107], "user": [109], "demands.": [110], "Specifically,": [111], "constructs": [114], "CoT": [116], "adaptation": [117], "via": [119], "two-stage": [121], "method": [122], "subsequently": [124], "applies": [125], "dual-tuning": [127], "strategy": [128], "fine-tune": [130], "for": [132], "generating": [133], "in": [136], "an": [137], "analyze-then-answer": [138], "pattern.": [139], "Experiments": [140], "demonstrate": [141], "improves": [144], "average": [146], "format": [147], "accuracy": [148], "content": [150], "correctness": [151], "of": [152], "LLM": [153], "35.4\\%": [156], "29.4\\%,": [158], "respectively,": [159], "achieving": [160], "state-of-the-art": [161], "(SOTA)": [162], "performance": [163], "other": [165], "competitive": [166], "baselines.": [167]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8598999977111816, "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": 0.8598999977111816, "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": 0.07680000364780426, "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": 0.02449999935925007, "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:2510.09211", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.09211", "pdf_url": "https://arxiv.org/pdf/2510.09211", "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/W4409221375", "doi": "https://doi.org/10.1080/10095020.2025.2483884", "title": "Design and application of a semantic-driven geospatial modeling knowledge graph based on large language models", "publication_year": 2025, "publication_date": "2025-04-07", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5055854355", "display_name": "Jianyuan Liang", "orcid": "https://orcid.org/0009-0004-7280-5788", "observed_orcids": ["https://orcid.org/0009-0004-7280-5788"]}, "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": "Jianyuan Liang", "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": "https://openalex.org/A5110860664", "display_name": "Shuyang Hou", "orcid": "https://orcid.org/0009-0000-6984-9959", "observed_orcids": ["https://orcid.org/0009-0000-6984-9959"]}, "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": "Shuyang Hou", "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": "https://openalex.org/A5110916424", "display_name": "Anqi Zhao", "orcid": "https://orcid.org/0000-0001-7511-6268", "observed_orcids": ["https://orcid.org/0000-0001-7511-6268"]}, "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": "Anqi Zhao", "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": "https://openalex.org/A5073591829", "display_name": "Qingyang Xu", "orcid": "https://orcid.org/0000-0001-8351-4944", "observed_orcids": ["https://orcid.org/0000-0001-8351-4944"]}, "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": "Qingyang Xu", "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": "https://openalex.org/A5089044672", "display_name": "Longgang Xiang", "orcid": "https://orcid.org/0000-0001-9022-6991", "observed_orcids": ["https://orcid.org/0000-0001-9022-6991"]}, "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": "Longgang Xiang", "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": "https://openalex.org/A5021251779", "display_name": "Rui Li", "orcid": "https://orcid.org/0000-0001-5167-2956", "observed_orcids": ["https://orcid.org/0000-0001-5167-2956", "https://orcid.org/0009-0005-0625-6802"]}, "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": "Rui Li", "raw_affiliation_strings": ["Wuhan University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Wuhan University", "institution_ids": ["https://openalex.org/I37461747"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5030670883", "display_name": "Huayi Wu", "orcid": "https://orcid.org/0000-0003-3971-0512", "observed_orcids": ["https://orcid.org/0000-0003-3971-0512"]}, "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": true, "raw_author_name": "Huayi Wu", "raw_affiliation_strings": ["Wuhan University"], "raw_orcid": "https://orcid.org/0000-0003-3971-0512", "affiliations": [{"raw_affiliation_string": "Wuhan University", "institution_ids": ["https://openalex.org/I37461747"]}]}], "abstract_inverted_index": {"While": [0], "leveraging": [1], "large": [2], "language": [3], "models": [4], "(LLMs)": [5], "for": [6, 36, 67, 86, 133, 170, 217, 240], "intelligent": [7], "geospatial": [8, 38, 171, 241], "modeling": [9, 39, 53, 58, 103, 130, 164, 199], "has": [10], "garnered": [11], "significant": [12], "attention,": [13], "the": [14, 73, 78, 84, 149, 175, 193, 206, 228], "limited": [15], "domain-specific": [16, 87], "knowledge": [17, 35, 96, 142, 158], "of": [18, 75, 80, 123, 230], "LLMs": [19, 169, 236], "often": [20], "leads": [21], "to": [22, 50, 72, 147, 160, 237], "inefficient": [23], "or": [24], "unreliable": [25], "geo-analysis": [26], "model": [27], "generation.": [28], "Crowdsourced": [29], "geoprocessing": [30, 62, 179], "scripts": [31, 63, 106, 180, 191], "encapsulate": [32], "extensive": [33], "expert": [34], "different": [37], "tasks,": [40], "where": [41], "code": [42, 76, 239], "snippets": [43], "are": [44, 113], "strategically": [45], "combined": [46], "into": [47], "functional": [48, 203, 219], "steps": [49], "build": [51], "application-specific": [52], "processes.": [54], "However,": [55], "extracting": [56], "these": [57, 218], "processes": [59, 104, 200], "from": [60, 105], "heterogeneous": [61], "and": [64, 83, 101, 119, 141, 166, 181], "integrating": [65], "them": [66], "reuse": [68], "remains": [69], "challenging": [70], "due": [71], "complexity": [74], "interdependencies,": [77], "heterogeneity": [79], "scripting": [81], "approaches,": [82], "need": [85], "customization.": [88], "To": [89], "address": [90], "this,": [91], "we": [92], "propose": [93], "S-GMKG,": [94, 231], "a": [95, 115, 120, 139, 155], "graph": [97], "that": [98, 189], "systematically": [99], "extracts": [100], "integrates": [102], "as": [107, 154, 198], "structured": [108], "semantic": [109], "units.": [110], "Two": [111], "strategies": [112, 208], "introduced:": [114], "skeleton-based": [116], "extraction": [117, 132], "method": [118], "knowledge-enhanced": [121], "chain": [122], "thought": [124], "(CoT)": [125], "approach,": [126], "which": [127], "facilitate": [128], "automated": [129], "process": [131, 144], "S-GMKG": [134, 152, 176, 194], "via": [135], "prompt": [136], "engineering.": [137], "Furthermore,": [138], "self-canonicalization": [140], "augmentation": [143], "is": [145], "proposed": [146, 207], "refine": [148], "S-GMKG.": [150], "Consequently,": [151], "serves": [153], "robust": [156], "external": [157], "source": [159], "provide": [161], "interpretable,": [162], "graph-based": [163], "solutions": [165], "synergizes": [167], "with": [168, 201, 205, 235], "tasks.": [172], "We": [173], "implemented": [174], "using": [177], "4820": [178], "evaluated": [182], "it": [183], "across": [184], "various": [185], "LLMs.": [186], "Results": [187], "indicate": [188], "most": [190], "in": [192, 214, 223, 233], "can": [195], "be": [196], "represented": [197], "3\u20137": [202], "steps,": [204], "achieving": [209], "3.2%\u201314.5%": [210], "higher": [211], "recall": [212], "rates": [213], "relationship": [215], "identification": [216], "steps.": [220], "Case": [221], "studies": [222], "two": [224], "distinct": [225], "scenarios": [226], "demonstrate": [227], "practicality": [229], "particularly": [232], "collaborating": [234], "generate": [238], "modeling.": [242]}, "primary_topic": {"id": "https://openalex.org/T10757", "display_name": "Geographic Information Systems Studies", "score": 0.26589998602867126, "subfield": {"id": "https://openalex.org/subfields/3305", "display_name": "Geography, Planning and Development"}, "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/T10757", "display_name": "Geographic Information Systems Studies", "score": 0.26589998602867126, "subfield": {"id": "https://openalex.org/subfields/3305", "display_name": "Geography, Planning and Development"}, "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/T10215", "display_name": "Semantic Web and Ontologies", "score": 0.2556000053882599, "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/T11986", "display_name": "Scientific Computing and Data Management", "score": 0.1509999930858612, "subfield": {"id": "https://openalex.org/subfields/1802", "display_name": "Information Systems and Management"}, "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": "doi:10.1080/10095020.2025.2483884", "is_oa": true, "landing_page_url": "https://doi.org/10.1080/10095020.2025.2483884", "pdf_url": null, "source": {"id": "https://openalex.org/S36798160", "display_name": "Geo-spatial Information Science", "issn_l": "1009-5020", "issn": ["1009-5020", "1993-5153"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "jufo-1", "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": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Geo-spatial Information Science", "raw_type": "journal-article"}, "cited_by_count": 12, "is_retracted": false}, {"id": "https://openalex.org/W4415286470", "doi": "https://doi.org/10.48550/arxiv.2503.01754", "title": "SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces", "publication_year": 2025, "publication_date": "2025-03-03", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5045718502", "display_name": "Guande Wu", "orcid": "https://orcid.org/0000-0002-9244-173X", "observed_orcids": ["https://orcid.org/0000-0002-9244-173X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Guande", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101697214", "display_name": "Huan Song", "orcid": "https://orcid.org/0000-0002-9639-9962", "observed_orcids": ["https://orcid.org/0000-0002-9639-9962"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Song, Huan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100434924", "display_name": "Yawei Wang", "orcid": "https://orcid.org/0000-0002-0427-7168", "observed_orcids": ["https://orcid.org/0000-0002-0427-7168"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yawei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119858288", "display_name": "Qiaojing Yan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yan, Qiaojing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5057838053", "display_name": "Yijun Tian", "orcid": "https://orcid.org/0000-0003-2795-6080", "observed_orcids": ["https://orcid.org/0000-0003-2795-6080"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tian, Yijun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5049488691", "display_name": "Lin Lee Cheong", "orcid": "https://orcid.org/0009-0006-8935-6602", "observed_orcids": ["https://orcid.org/0009-0006-8935-6602"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cheong, Lin Lee", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5039231829", "display_name": "Panpan Xu", "orcid": "https://orcid.org/0000-0001-8180-7460", "observed_orcids": ["https://orcid.org/0000-0001-8180-7460"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Panpan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Reasoning": [0], "is": [1], "increasingly": [2], "crucial": [3], "for": [4, 85, 109], "various": [5], "tasks.": [6], "While": [7], "chain-of-thought": [8], "prompting": [9], "enables": [10], "large": [11], "language": [12], "models": [13], "to": [14, 61, 65, 76, 90, 117, 128], "leverage": [15], "reasoning": [16, 20, 41, 63, 74, 93, 131], "effectively,": [17], "harnessing": [18], "the": [19, 40, 44, 88, 92, 98, 144], "capabilities": [21, 42], "of": [22, 43], "Vision-Language": [23], "Models": [24], "(VLMs)": [25], "remains": [26], "challenging.": [27], "To": [28], "solve": [29], "this": [30], "problem,": [31], "we": [32, 96], "propose": [33], "a": [34, 57, 72, 113], "novel": [35], "self-distillation": [36], "framework": [37, 48], "that": [38, 139], "enhances": [39], "model.": [45], "The": [46], "proposed": [47], "introduces": [49], "several": [50, 102], "key": [51], "innovations.": [52], "We": [53], "start": [54], "by": [55], "employing": [56], "prompt": [58], "library": [59], "tailored": [60], "visual": [62], "tasks": [64], "generate": [66], "diverse": [67, 130], "in-context": [68, 134], "questions": [69], "and": [70, 123], "utilize": [71], "two-step": [73], "procedure": [75], "derive": [77], "reasoning-guided": [78], "responses.": [79], "These": [80], "responses": [81], "are": [82], "then": [83], "used": [84], "self-distillation,": [86], "enabling": [87], "model": [89, 99], "internalize": [91], "process.": [94], "Additionally,": [95], "improve": [97], "architecture": [100], "with": [101], "innovative": [103], "components,": [104], "including": [105], "an": [106, 124], "intervention": [107], "adapter": [108], "efficient": [110], "parameter": [111], "updates,": [112], "cross-modal": [114], "skip": [115], "connection": [116], "facilitate": [118], "information": [119], "exchange": [120], "between": [121], "modalities,": [122], "ensemble": [125], "learning": [126], "algorithm": [127], "integrate": [129], "from": [132], "multiple": [133], "questions.": [135], "Extensive": [136], "experiments": [137], "show": [138], "our": [140], "method": [141], "significantly": [142], "improves": [143], "baseline": [145], "performance": [146], "across": [147], "five": [148], "VQA": [149], "datasets.": [150]}, "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/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"}}, {"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:2503.01754", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.01754", "pdf_url": "https://arxiv.org/pdf/2503.01754", "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/W7132993116", "doi": null, "title": "Prompting Strategies for Large Language Models in Requirements Elicitation : A Systematic Literature Review", "publication_year": 2025, "publication_date": "2025-01-01", "type": "review", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5005984167", "display_name": "Naveed Ali", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I166825849", "display_name": "Tampere University", "ror": "https://ror.org/033003e23", "country_code": "FI", "type": "education", "lineage": ["https://openalex.org/I166825849"]}], "countries": ["FI"], "is_corresponding": true, "raw_author_name": "Ali, Naveed", "raw_affiliation_strings": ["Tampere University Master's Degree Programme in Computing Sciences"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tampere University Master's Degree Programme in Computing Sciences", "institution_ids": ["https://openalex.org/I166825849"]}]}], "abstract_inverted_index": {"Recent": [0], "advancements": [1], "in": [2, 30, 190, 207], "Large": [3], "Language": [4], "Models": [5], "(LLMs)": [6], "such": [7, 160], "as": [8, 161], "GPT-4,": [9], "DeepSeek,": [10], "Gemini,": [11], "and": [12, 27, 47, 63, 75, 80, 109, 120, 130, 137, 155, 167, 195, 213, 215, 224, 232, 240], "LLaMA": [13], "have": [14], "introduced": [15], "new": [16], "opportunities": [17], "for": [18, 100, 230], "supporting": [19, 158], "requirements": [20, 101], "elicitation,": [21, 209], "one": [22], "of": [23, 36, 53, 90, 204], "the": [24, 121], "most": [25], "knowledge-intensive": [26], "error-prone": [28], "activities": [29], "Requirements": [31], "Engineering": [32], "(RE).": [33], "The": [34, 103, 141, 171, 198], "effectiveness": [35], "LLM-assisted": [37], "elicitation": [38, 181, 244], "depends": [39], "largely": [40], "on": [41], "how": [42, 175], "prompts": [43], "are": [44], "designed,": [45], "structured,": [46], "contextualized.": [48], "As": [49], "a": [50, 68, 86, 126, 132, 201], "wide": [51], "range": [52], "prompting": [54, 95, 144, 176, 205, 238], "strategies": [55, 96, 145, 239], "has": [56], "emerged,": [57], "including": [58, 149], "zero-shot,": [59], "few-shot,": [60], "chain-of-thought,": [61], "role-based,": [62], "prompt-chaining": [64], "techniques,": [65], "there": [66], "is": [67, 177], "growing": [69], "need": [70], "to": [71, 235], "consolidate": [72], "current": [73], "evidence": [74], "evaluate": [76], "their": [77, 150], "strengths,": [78], "limitations,": [79], "practical": [81], "relevance.": [82], "This": [83], "thesis": [84], "presents": [85], "systematic": [87], "literature": [88], "review": [89, 104, 172, 227], "58": [91], "peer-reviewed": [92], "studies": [93], "investigating": [94], "used": [97], "with": [98, 157], "LLMs": [99], "elicitation.": [102], "follows": [105], "established": [106], "SLR": [107], "guidelines": [108], "PRISMA": [110], "2020": [111], "procedures.": [112], "Studies": [113], "were": [114], "retrieved": [115], "from": [116], "Scopus,": [117], "IEEE": [118], "Xplore,": [119], "ACM": [122], "Digital": [123], "Library": [124], "using": [125], "unified": [127], "search": [128], "strategy": [129], "underwent": [131], "structured": [133], "screening,": [134], "quality": [135], "assessment,": [136], "data": [138], "extraction": [139], "process.": [140], "findings": [142], "categorize": [143], "across": [146, 179], "multiple": [147], "dimensions,": [148], "structural": [151], "design,": [152], "reasoning": [153], "mechanisms,": [154], "integration": [156], "tools": [159], "retrieval-augmented": [162], "generation": [163], "pipelines,": [164], "conversational": [165], "agents,": [166], "domain-specific": [168], "knowledge": [169], "models.": [170], "also": [173], "synthesizes": [174], "applied": [178], "key": [180], "contexts.": [182], "Furthermore,": [183], "it": [184], "examines": [185], "evaluation": [186], "approaches,": [187], "highlighting": [188], "trends": [189], "quantitative": [191], "metrics,": [192], "expert": [193], "judgment,": [194], "mixed-method": [196], "assessment.": [197], "study": [199], "contributes": [200], "consolidated": [202], "view": [203], "practices": [206], "LLM-based": [208], "identifies": [210], "recurring": [211], "benefits": [212], "challenges,": [214], "outlines": [216], "emerging": [217], "best": [218], "practices.": [219], "By": [220], "synthesizing": [221], "methodological": [222], "patterns": [223], "gaps,": [225], "this": [226], "offers": [228], "guidance": [229], "researchers": [231], "practitioners": [233], "seeking": [234], "design": [236], "effective": [237], "develop": [241], "reliable,": [242], "human-centered": [243], "workflows": [245], "supported": [246], "by": [247], "generative": [248], "AI.": [249]}, "primary_topic": {"id": "https://openalex.org/T10430", "display_name": "Software Engineering Techniques and Practices", "score": 0.8931000232696533, "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/T10430", "display_name": "Software Engineering Techniques and Practices", "score": 0.8931000232696533, "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/T10639", "display_name": "Advanced Software Engineering Methodologies", "score": 0.0284000001847744, "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/T10260", "display_name": "Software Engineering Research", "score": 0.019099999219179153, "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": "pmh:oai:trepo.tuni.fi:10024/232320", "is_oa": true, "landing_page_url": "https://trepo.tuni.fi/handle/10024/232320", "pdf_url": "https://trepo.tuni.fi/bitstream/10024/232320/2/AliNaveed.pdf", "source": {"id": "https://openalex.org/S4306401860", "display_name": "Tampere University Institutional Repository (Tampere University)", "issn_l": null, "issn": null, "is_oa": false, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/I150589677", "host_organization_name": "Tampere University of Applied Sciences", "host_organization_lineage": ["https://openalex.org/I150589677"], "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": "fi= Pro gradu -tutkielma | en=Master's thesis|"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417537343", "doi": "https://doi.org/10.48550/arxiv.2506.15894", "title": "Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning", "publication_year": 2025, "publication_date": "2025-06-18", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Silver, Sam", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Silver, Sam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Sun, Jimin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Jimin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhang, Ivan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ivan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Hooker, Sara", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hooker, Sara", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Kim, Eddie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kim, Eddie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4], "demonstrated": [5], "impressive": [6], "mathematical": [7], "reasoning": [8, 25], "capabilities,": [9], "yet": [10], "their": [11, 62], "performance": [12], "remains": [13], "brittle": [14], "to": [15, 28, 56, 88], "minor": [16], "variations": [17], "in": [18, 116, 137], "problem": [19], "description": [20], "and": [21, 81, 91], "prompting": [22], "strategy.": [23], "Furthermore,": [24], "is": [26], "vulnerable": [27], "sampling-induced": [29], "errors": [30], "which": [31], "autoregressive": [32], "models": [33, 80], "must": [34], "primarily": [35], "address": [36], "using": [37], "self-correction": [38, 45, 73, 111], "via": [39], "additionally-generated": [40], "tokens.": [41], "To": [42], "better": [43], "understand": [44], "capabilities": [46, 112], "of": [47, 64, 78, 93, 121, 132], "recent": [48, 126], "models,": [49], "we": [50], "conduct": [51], "experiments": [52], "measuring": [53], "models'": [54], "ability": [55, 123], "self-correct": [57], "synthetic": [58], "perturbations": [59], "introduced": [60], "into": [61], "Chain": [63], "Thought": [65], "(CoT)": [66], "reasoning.": [67], "We": [68], "observe": [69], "robust": [70], "single-utterance": [71], "intrinsic": [72, 110], "behavior": [74], "across": [75], "a": [76], "range": [77], "open-weight": [79], "datasets,": [82], "ranging": [83], "from": [84], "subtle,": [85], "implicit": [86], "corrections": [87, 92], "explicit": [89], "acknowledgments": [90], "errors.": [94], "Our": [95], "findings": [96], "suggest": [97], "that": [98, 125], "LLMs,": [99], "including": [100], "those": [101], "not": [102], "finetuned": [103], "for": [104], "long": [105], "CoT,": [106], "may": [107], "possess": [108], "stronger": [109], "than": [113], "commonly": [114], "shown": [115], "the": [117], "literature.": [118], "The": [119], "presence": [120], "this": [122], "suggests": [124], "\"reasoning\"": [127], "model": [128], "work": [129], "involves": [130], "amplification": [131], "traits": [133], "already": [134], "meaningfully": [135], "present": [136], "models.": [138]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7705000042915344, "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": 0.7705000042915344, "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": 0.11559999734163284, "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": 0.019700000062584877, "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:2506.15894", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.15894", "pdf_url": "https://arxiv.org/pdf/2506.15894", "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/W4416043159", "doi": "https://doi.org/10.48550/arxiv.2502.18729", "title": "Random Forest-of-Thoughts: Uncertainty-aware Reasoning for Computational Social Science", "publication_year": 2025, "publication_date": "2025-02-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102010375", "display_name": "Xiaohua Wu", "orcid": "https://orcid.org/0000-0001-7692-7863", "observed_orcids": ["https://orcid.org/0000-0001-7692-7863"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Xiaohua", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065941595", "display_name": "Xiaohui Tao", "orcid": "https://orcid.org/0000-0002-0020-077X", "observed_orcids": ["https://orcid.org/0000-0002-0020-077X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tao, Xiaohui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5017888530", "display_name": "Wenjie Wu", "orcid": "https://orcid.org/0009-0001-6727-671X", "observed_orcids": ["https://orcid.org/0009-0001-6727-671X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Wenjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100627260", "display_name": "Yuefeng Li", "orcid": "https://orcid.org/0000-0002-9548-5957", "observed_orcids": ["https://orcid.org/0000-0002-9548-5957", "https://orcid.org/0009-0003-9097-692X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Yuefeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100412815", "display_name": "Lin Li", "orcid": "https://orcid.org/0000-0001-7553-6916", "observed_orcids": ["https://orcid.org/0000-0001-7553-6916"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Lin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Social": [0], "surveys": [1], "in": [2, 38, 89], "computational": [3, 123, 174], "social": [4, 42, 124, 175, 185, 202], "science": [5, 176], "are": [6], "well-designed": [7], "by": [8, 64, 134], "elaborate": [9], "domain": [10], "theories": [11], "that": [12, 91, 192], "can": [13, 86, 151], "effectively": [14], "reflect": [15], "the": [16, 32, 39, 45, 48, 120, 142, 146, 153, 162], "interviewee's": [17, 33], "deep": [18], "thoughts": [19], "without": [20], "concealing": [21], "their": [22], "true": [23], "feelings.": [24], "The": [25, 51, 126, 168], "candidate": [26], "questionnaire": [27], "options": [28], "highly": [29], "depend": [30], "on": [31, 178, 199], "previous": [34], "answer,": [35], "which": [36], "results": [37], "complexity": [40], "of": [41, 53, 109, 122, 148, 157, 166, 184], "survey": [43, 186, 203], "analysis,": [44], "time,": [46], "and": [47, 94, 139, 155], "expertise": [49], "required.": [50], "ability": [52], "large": [54, 101], "language": [55, 102, 196], "models": [56], "(LLMs)": [57], "to": [58, 74, 118, 130, 144, 172], "perform": [59, 131], "complex": [60], "reasoning": [61, 117], "is": [62, 112, 170], "well-enhanced": [63], "prompting": [65, 104], "learning": [66], "such": [67], "as": [68], "Chain-of-thought": [69], "(CoT)": [70], "but": [71], "still": [72], "confined": [73], "left-to-right": [75], "decision-making": [76, 133], "processes": [77], "or": [78], "limited": [79], "paths": [80], "during": [81], "inference.": [82], "This": [83], "means": [84], "they": [85], "fall": [87], "short": [88], "problems": [90, 205], "require": [92], "exploration": [93, 154], "uncertainty": [95, 116], "searching.": [96], "In": [97], "response,": [98], "a": [99, 182], "novel": [100, 201], "model": [103], "method,": [105], "called": [106], "Random": [107], "Forest": [108], "Thoughts": [110], "(RFoT),": [111], "proposed": [113], "for": [114], "generating": [115, 135], "fit": [119], "area": [121], "science.": [125], "RFoT": [127, 193], "allows": [128], "LLMs": [129], "deliberate": [132], "diverse": [136], "thought": [137], "space": [138, 165], "randomly": [140], "selecting": [141], "sub-thoughts": [143], "build": [145], "forest": [147], "thoughts.": [149], "It": [150], "extend": [152], "prediction": [156], "overall": [158], "performance,": [159], "benefiting": [160], "from": [161], "extensive": [163], "research": [164], "response.": [167], "method": [169], "applied": [171], "optimize": [173], "analysis": [177, 187, 204], "two": [179, 200], "datasets": [180], "covering": [181], "spectrum": [183], "problems.": [188], "Our": [189], "experiments": [190], "show": [191], "significantly": [194], "enhances": [195], "models'": [197], "abilities": [198], "requiring": [206], "non-trivial": [207], "reasoning.": [208]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7724999785423279, "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": 0.7724999785423279, "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/T13910", "display_name": "Computational and Text Analysis Methods", "score": 0.07900000363588333, "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/T10181", "display_name": "Natural Language Processing Techniques", "score": 0.04580000042915344, "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:2502.18729", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.18729", "pdf_url": "https://arxiv.org/pdf/2502.18729", "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/W4410050652", "doi": "https://doi.org/10.1016/j.aei.2025.103422", "title": "A context-aware KG-LLM collaborated conceptual design approach for personalized products: A case in lower limbs rehabilitation assistive devices", "publication_year": 2025, "publication_date": "2025-05-03", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101809181", "display_name": "Xinyu Pan", "orcid": "https://orcid.org/0000-0001-9951-4842", "observed_orcids": ["https://orcid.org/0000-0001-9951-4842"]}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xinyu Pan", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5046678554", "display_name": "Weibin Zhuang", "orcid": "https://orcid.org/0000-0002-4061-538X", "observed_orcids": ["https://orcid.org/0000-0002-4061-538X"]}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Weibin Zhuang", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5083914100", "display_name": "Sijie Wen", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Sijie Wen", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103332299", "display_name": "Weigang Yu", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Weigang Yu", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061529100", "display_name": "Jinsong Bao", "orcid": "https://orcid.org/0000-0003-1999-1003", "observed_orcids": ["https://orcid.org/0000-0003-1999-1003"]}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jinsong Bao", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100406106", "display_name": "Xinyu Li", "orcid": "https://orcid.org/0000-0002-4117-9698", "observed_orcids": ["https://orcid.org/0000-0002-4117-9698", "https://orcid.org/0009-0001-4040-6588", "https://orcid.org/0009-0005-5378-3947"]}, "institutions": [{"id": "https://openalex.org/I181326427", "display_name": "Donghua University", "ror": "https://ror.org/035psfh38", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I181326427"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xinyu Li", "raw_affiliation_strings": ["College of Mechanical Engineering, Donghua University, Shanghai 201620, China"], "raw_orcid": "https://orcid.org/0000-0002-4117-9698", "affiliations": [{"raw_affiliation_string": "College of Mechanical Engineering, Donghua University, Shanghai 201620, China", "institution_ids": ["https://openalex.org/I181326427"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10672", "display_name": "Design Education and Practice", "score": 0.9887999892234802, "subfield": {"id": "https://openalex.org/subfields/2210", "display_name": "Mechanical 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/T10672", "display_name": "Design Education and Practice", "score": 0.9887999892234802, "subfield": {"id": "https://openalex.org/subfields/2210", "display_name": "Mechanical 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/T11729", "display_name": "Product Development and Customization", "score": 0.0012000000569969416, "subfield": {"id": "https://openalex.org/subfields/1405", "display_name": "Management of Technology and Innovation"}, "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/T11023", "display_name": "Prosthetics and Rehabilitation Robotics", "score": 0.0007999999797903001, "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"}}], "primary_location": {"id": "doi:10.1016/j.aei.2025.103422", "is_oa": false, "landing_page_url": "https://doi.org/10.1016/j.aei.2025.103422", "pdf_url": null, "source": {"id": "https://openalex.org/S112141509", "display_name": "Advanced Engineering Informatics", "issn_l": "1474-0346", "issn": ["1474-0346", "1873-5320"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["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": "Advanced Engineering Informatics", "raw_type": "journal-article"}, "cited_by_count": 27, "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/W4411449792", "doi": "https://doi.org/10.1145/3715761", "title": "Integrating Large Language Models and Reinforcement Learning for Non-linear Reasoning", "publication_year": 2025, "publication_date": "2025-06-19", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yoav Alon", "orcid": "https://orcid.org/0000-0003-1432-3057", "observed_orcids": ["https://orcid.org/0000-0003-1432-3057"]}, "institutions": [{"id": "https://openalex.org/I36234482", "display_name": "University of Bristol", "ror": "https://ror.org/0524sp257", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I36234482"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Yoav Alon", "raw_affiliation_strings": ["University of Bristol, Bristol, United Kingdom"], "raw_orcid": "https://orcid.org/0000-0003-1432-3057", "affiliations": [{"raw_affiliation_string": "University of Bristol, Bristol, United Kingdom", "institution_ids": ["https://openalex.org/I36234482"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5072292925", "display_name": "Cristina David", "orcid": "https://orcid.org/0000-0002-9106-934X", "observed_orcids": ["https://orcid.org/0000-0002-9106-934X"]}, "institutions": [{"id": "https://openalex.org/I36234482", "display_name": "University of Bristol", "ror": "https://ror.org/0524sp257", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I36234482"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Cristina David", "raw_affiliation_strings": ["University of Bristol, Bristol, United Kingdom"], "raw_orcid": "https://orcid.org/0000-0002-9106-934X", "affiliations": [{"raw_affiliation_string": "University of Bristol, Bristol, United Kingdom", "institution_ids": ["https://openalex.org/I36234482"]}]}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "were": [4, 69], "shown": [5], "to": [6, 48], "struggle": [7], "with": [8], "long-term": [9, 92], "planning,": [10], "which": [11, 20, 68], "may": [12], "be": [13], "caused": [14], "by": [15, 73, 98], "the": [16, 23, 44, 57, 74, 79, 89, 109, 129, 133, 137], "limited": [17], "way": [18], "in": [19], "they": [21], "explore": [22], "space": [24, 41], "of": [25, 59, 118, 123], "possible": [26], "solutions.": [27], "We": [28, 94, 104, 126], "propose": [29], "an": [30, 39], "architecture": [31, 107], "where": [32], "a": [33], "Reinforcement": [34], "Learning": [35], "(RL)": [36], "Agent": [37, 45], "guides": [38], "LLM\u2019s": [40, 75], "exploration:": [42], "(1)": [43], "has": [46], "access": [47], "domainspecific": [49], "information,": [50], "and": [51, 65, 102, 113, 121, 136, 147], "can": [52, 81], "therefore": [53], "make": [54], "decisions": [55], "about": [56], "quality": [58], "candidate": [60], "solutions": [61], "based": [62], "on": [63, 83, 108], "specific": [64], "relevant": [66], "metrics,": [67], "not": [70], "explicitly": [71], "considered": [72], "training": [76], "objective;": [77], "(2)": [78], "LLM": [80], "focus": [82], "generating": [84], "immediate": [85], "next": [86], "steps,": [87], "without": [88], "need": [90], "for": [91], "planning.": [93], "allow": [95], "non-linear": [96], "reasoning": [97, 139], "exploring": [99], "alternative": [100], "paths": [101], "backtracking.": [103], "evaluate": [105], "this": [106], "program": [110], "equivalence": [111], "task,": [112, 131], "compare": [114], "it": [115], "against": [116, 145], "Chain": [117], "Thought": [119], "(CoT)": [120], "Tree": [122], "Thoughts": [124], "(ToT).": [125], "assess": [127], "both": [128], "downstream": [130], "denoting": [132], "binary": [134], "classification,": [135], "intermediate": [138], "steps.": [140], "Our": [141], "approach": [142], "compares": [143], "positively": [144], "CoT": [146], "ToT.": [148]}, "primary_topic": {"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.4456000030040741, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.4456000030040741, "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": 0.17649999260902405, "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/T10260", "display_name": "Software Engineering Research", "score": 0.1096000000834465, "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:10.1145/3715761", "is_oa": true, "landing_page_url": "https://doi.org/10.1145/3715761", "pdf_url": "https://dl.acm.org/doi/pdf/10.1145/3715761", "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": null, "license_id": null, "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": 0, "is_retracted": false}, {"id": "https://openalex.org/W4410888023", "doi": "https://doi.org/10.31234/osf.io/86xsj_v19", "title": "WITHDRAWN", "publication_year": 2025, "publication_date": "2025-05-30", "type": "preprint", "language": "en", "authorships": [], "abstract_inverted_index": {"Given": [0], "its": [1], "ubiquity": [2], "in": [3, 11, 21, 30, 48], "mental": [4], "life,": [5], "the": [6, 23, 59, 71, 97, 101, 114, 134, 156, 198], "precise": [7], "role": [8, 47], "of": [9, 26, 162, 200], "language": [10, 183], "enabling": [12, 118], "complex": [13], "thought": [14], "and": [15, 54, 86, 108, 125, 155, 181], "reasoning": [16, 29, 160], "remains": [17], "difficult": [18], "to": [19, 104, 113, 120, 136], "study": [20], "humans.However,": [22], "surprising": [24], "emergence": [25], "sophisticated": [27], "symbolic": [28, 89, 94, 110, 142, 179], "purely": [31], "connectionist": [32, 176], "Large": [33], "Language": [34], "Models": [35], "(LLMs)-systems": [36], "learning": [37, 177], "only": [38], "from": [39, 70, 145], "text-provides": [40], "a": [41, 56, 80, 139, 172, 190], "novel": [42], "empirical": [43], "lens": [44], "on": [45], "language's": [46], "cognition,": [49], "disrupting": [50], "historical": [51], "symbolic-connectionist": [52], "dichotomies": [53], "compelling": [55], "re-evaluation.We": [57], "introduce": [58], "Emergent": [60], "Symbolic": [61], "Cognition": [62], "(ESC)": [63], "framework,": [64], "proposing": [65], "that": [66, 92], "general": [67, 201], "intelligence": [68], "arises": [69], "dynamic": [72], "interaction": [73], "between": [74], "an": [75, 87, 185], "adaptive": [76], "continuous": [77], "substrate": [78, 102, 135], "(like": [79], "brain": [81], "or": [82, 205], "Artificial": [83], "Neural": [84], "Network)": [85], "internalized": [88], "framework.ESC": [90], "posits": [91], "recursive": [93], "generation": [95], "is": [96], "core": [98], "computational": [99], "engine:": [100], "learns": [103], "sequentially": [105], "generate,": [106], "process,": [107], "evaluate": [109], "sequences": [111], "according": [112], "framework's": [115], "implicit": [116], "rules,": [117], "it": [119], "navigate": [121], "vast": [122], "combinatorial": [123], "spaces": [124], "construct": [126], "structured": [127], "solutions": [128], "for": [129, 193], "diverse": [130], "problems.This": [131], "process": [132], "allows": [133], "operate": [137], "as": [138, 184], "powerful,": [140], "discrete": [141], "processor.Converging": [143], "evidence": [144], "human": [146], "cognitive": [147, 187], "development,": [148], "inner": [149], "speech,": [150], "neuroscience": [151], "(aphasia,": [152], "DMN": [153], "activity),": [154], "striking,": [157], "though": [158], "nascent,": [159], "abilities": [161], "LLMs": [163], "(e.g.,": [164], "chain-of-thought,": [165], "crossdomain": [166], "transfer)": [167], "supports": [168], "ESC.This": [169], "framework": [170], "offers": [171], "unifying": [173], "perspective,": [174], "reconciling": [175], "with": [178], "competence": [180], "reframing": [182], "inherited": [186], "engine,": [188], "establishing": [189], "conceptual": [191], "scaffold": [192], "future": [194], "interdisciplinary": [195], "inquiry": [196], "into": [197], "foundations": [199], "intelligence,": [202], "whether": [203], "biological": [204], "artificial.": [206]}, "primary_topic": {"id": "https://openalex.org/T14394", "display_name": "Cognitive Science and Education Research", "score": 0.27730000019073486, "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"}}, "topics": [{"id": "https://openalex.org/T14394", "display_name": "Cognitive Science and Education Research", "score": 0.27730000019073486, "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/T10258", "display_name": "Philosophy and Theoretical Science", "score": 0.13500000536441803, "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": 0.09210000187158585, "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:10.31234/osf.io/86xsj_v19", "is_oa": true, "landing_page_url": "https://doi.org/10.31234/osf.io/86xsj_v19", "pdf_url": "https://osf.io/86xsj_v19/download", "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/W4416430631", "doi": "https://doi.org/10.2139/ssrn.5767782", "title": "Using LLMs for Peer Review Simulation and Revision Planning in Clinical Research", "publication_year": 2025, "publication_date": "2025-01-01", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5086932309", "display_name": "Ricardo S. Pietrobon", "orcid": "https://orcid.org/0000-0003-2996-2193", "observed_orcids": ["https://orcid.org/0000-0003-2996-2193"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Ricardo Pietrobon", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061180963", "display_name": "Aline Machiavelli", "orcid": "https://orcid.org/0000-0002-5804-3826", "observed_orcids": ["https://orcid.org/0000-0002-5804-3826"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Aline Machiavelli", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Luiza Paulsen Rodrigues", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luiza Paulsen Rodrigues", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5116615815", "display_name": "Amit Agrey", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Amit Agrey", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5116615816", "display_name": "Lizzy Nkeangnyi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lizzy Nkeangnyi", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117136138", "display_name": "Giselle Zechia", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Giselle Zechia", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119589820", "display_name": "Antonio Lindenberg", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Antonio Lindenberg", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113127450", "display_name": "Victor Galv\u00e3o", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Victor Galv\u00e3o", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5044829081", "display_name": "Lucas Teixeira", "orcid": "https://orcid.org/0000-0003-3615-1567", "observed_orcids": ["https://orcid.org/0000-0003-3615-1567"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lucas Teixeira", "raw_affiliation_strings": ["SporeData Inc"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "SporeData Inc", "institution_ids": []}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.4255000054836273, "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": 0.4255000054836273, "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/T12648", "display_name": "Academic Writing and Publishing", "score": 0.3659999966621399, "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"}}, {"id": "https://openalex.org/T10206", "display_name": "Meta-analysis and systematic reviews", "score": 0.06629999727010727, "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"}}], "primary_location": {"id": "doi:10.2139/ssrn.5767782", "is_oa": true, "landing_page_url": "https://doi.org/10.2139/ssrn.5767782", "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/W4415948651", "doi": "https://doi.org/10.48550/arxiv.2510.16059", "title": "SIADAFIX: issue description response for adaptive program repair", "publication_year": 2025, "publication_date": "2025-10-17", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5120275611", "display_name": "Xin Cao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Cao, Xin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5120275612", "display_name": "Nan Yu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yu, Nan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0], "propose": [1], "utilizing": [2], "fast": [3, 56, 99], "and": [4, 54, 63, 90, 104, 143], "slow": [5, 43], "thinking": [6, 44, 57], "to": [7, 48, 61, 72], "enhance": [8], "the": [9, 74, 114, 119, 127], "capabilities": [10], "of": [11, 76], "large": [12], "language": [13], "model-based": [14], "agents": [15], "on": [16, 33, 94, 113], "complex": [17, 50, 109], "tasks": [18], "such": [19], "as": [20], "program": [21, 29, 51, 150], "repair.": [22, 151], "In": [23], "particular,": [24], "we": [25], "design": [26], "an": [27], "adaptive": [28], "repair": [30, 52, 85, 141], "method": [31, 41, 121], "based": [32, 93], "issue": [34, 65, 68], "description": [35, 69], "response,": [36], "called": [37], "SIADAFIX.": [38], "The": [39], "proposed": [40, 120], "utilizes": [42], "bug": [45, 77], "fix": [46, 78], "agent": [47, 79], "complete": [49], "tasks,": [53], "employs": [55, 98], "workflow": [58], "decision": [59], "components": [60], "optimize": [62], "classify": [64], "descriptions,": [66], "using": [67, 126], "response": [70], "results": [71, 112], "guide": [73], "orchestration": [75], "workflows.": [80], "SIADAFIX": [81, 138], "adaptively": [82], "selects": [83], "three": [84], "modes,": [86], "i.e.,": [87], "easy,": [88], "middle": [89], "hard": [91], "mode,": [92], "problem": [95], "complexity.": [96], "It": [97], "generalization": [100], "for": [101, 108, 148], "simple": [102], "problems": [103], "test-time": [105], "scaling": [106], "techniques": [107], "problems.": [110], "Experimental": [111], "SWE-bench": [115], "Lite": [116], "show": [117], "that": [118], "achieves": [122], "60.67%": [123], "pass@1": [124], "performance": [125], "Claude-4": [128], "Sonnet": [129], "model,": [130], "reaching": [131], "state-of-the-art": [132], "levels": [133], "among": [134], "all": [135], "open-source": [136], "methods.": [137], "effectively": [139], "balances": [140], "efficiency": [142], "accuracy,": [144], "providing": [145], "new": [146], "insights": [147], "automated": [149], "Our": [152], "code": [153], "is": [154], "available": [155], "at": [156], "https://github.com/liauto-siada/siada-cli.": [157]}, "primary_topic": {"id": "https://openalex.org/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.7559000253677368, "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"}}, "topics": [{"id": "https://openalex.org/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.7559000253677368, "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"}}, {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.24210000038146973, "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/T11975", "display_name": "Evolutionary Algorithms and Applications", "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:2510.16059", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.16059", "pdf_url": "https://arxiv.org/pdf/2510.16059", "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/W4414851187", "doi": "https://doi.org/10.48550/arxiv.2502.17807", "title": "DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities", "publication_year": 2025, "publication_date": "2025-02-25", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5085025479", "display_name": "Tianyi Zhuang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhuang, Tianyi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Kuang, Chuqiao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kuang, Chuqiao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100373874", "display_name": "Xiaoguang Li", "orcid": "https://orcid.org/0000-0003-4580-4865", "observed_orcids": ["https://orcid.org/0000-0003-4580-4865"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xiaoguang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102573328", "display_name": "Yihua Teng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Teng, Yihua", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5112882104", "display_name": "Jihao Wu", "orcid": "https://orcid.org/0000-0003-3235-0446", "observed_orcids": ["https://orcid.org/0000-0003-3235-0446"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Jihao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115592503", "display_name": "Yasheng Wang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yasheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5046228314", "display_name": "Lifeng Shang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shang, Lifeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0], "present": [1], "DocPuzzle,": [2], "a": [3, 40], "rigorously": [4], "constructed": [5], "benchmark": [6, 18], "for": [7, 62], "evaluating": [8], "long-context": [9], "reasoning": [10, 26, 64, 75, 92, 109], "capabilities": [11, 110], "in": [12, 66], "large": [13], "language": [14], "models": [15, 76, 86, 93], "(LLMs).": [16], "This": [17], "comprises": [19], "100": [20], "expert-level": [21], "QA": [22], "problems": [23], "requiring": [24], "multi-step": [25], "over": [27], "long": [28], "real-world": [29], "documents.": [30], "To": [31], "ensure": [32], "the": [33, 99, 106], "task": [34], "quality": [35], "and": [36, 79], "complexity,": [37], "we": [38], "implement": [39], "human-AI": [41], "collaborative": [42], "annotation-validation": [43], "pipeline.": [44], "DocPuzzle": [45], "introduces": [46], "an": [47], "innovative": [48], "evaluation": [49, 69], "framework": [50], "that": [51], "mitigates": [52], "guessing": [53], "bias": [54], "through": [55], "checklist-guided": [56], "process": [57], "analysis,": [58], "establishing": [59], "new": [60], "standards": [61], "assessing": [63], "capacities": [65], "LLMs.": [67], "Our": [68], "results": [70], "show": [71], "that:": [72], "1)Advanced": [73], "slow-thinking": [74], "like": [77, 87, 94], "o1-preview(69.7%)": [78], "DeepSeek-R1(66.3%)": [80], "significantly": [81], "outperform": [82], "best": [83], "general": [84], "instruct": [85], "Claude": [88], "3.5": [89], "Sonnet(57.7%);": [90], "2)Distilled": [91], "DeepSeek-R1-Distill-Qwen-32B(41.3%)": [95], "falls": [96], "far": [97], "behind": [98], "teacher": [100], "model,": [101], "suggesting": [102], "challenges": [103], "to": [104], "maintain": [105], "generalization": [107], "of": [108], "relying": [111], "solely": [112], "on": [113], "distillation.": [114]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9491999745368958, "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": 0.9491999745368958, "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": 0.021800000220537186, "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": 0.01810000091791153, "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:2502.17807", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.17807", "pdf_url": "https://arxiv.org/pdf/2502.17807", "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/W4417257970", "doi": "https://doi.org/10.48550/arxiv.2506.08935", "title": "Can A Gamer Train A Mathematical Reasoning Model?", "publication_year": 2025, "publication_date": "2025-06-10", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5103066975", "display_name": "Andrew Young Shin", "orcid": "https://orcid.org/0000-0001-6713-0609", "observed_orcids": ["https://orcid.org/0000-0001-6713-0609"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Shin, Andrew", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"While": [0], "large": [1], "language": [2], "models": [3, 93], "(LLMs)": [4], "have": [5, 24], "achieved": [6], "remarkable": [7], "performance": [8, 87], "in": [9, 97], "various": [10], "tasks": [11], "including": [12], "mathematical": [13, 55, 72, 89, 107], "reasoning,": [14], "their": [15], "development": [16], "typically": [17], "demands": [18], "prohibitive": [19], "computational": [20], "resources.": [21], "Recent": [22], "advancements": [23], "reduced": [25], "costs": [26], "for": [27], "training": [28], "capable": [29], "models,": [30], "yet": [31], "even": [32], "these": [33], "approaches": [34], "rely": [35], "on": [36, 75, 88], "high-end": [37], "hardware": [38], "clusters.": [39], "In": [40], "this": [41], "paper,": [42], "we": [43, 67], "demonstrate": [44], "that": [45, 82, 105], "a": [46, 53, 69], "single": [47], "average": [48], "gaming": [49], "GPU": [50], "can": [51], "train": [52, 68], "solid": [54], "reasoning": [56, 73, 90, 108], "model,": [57], "by": [58], "integrating": [59], "reinforcement": [60], "learning": [61], "and": [62], "memory": [63, 81], "optimization": [64], "techniques.": [65], "Specifically,": [66], "1.5B": [70], "parameter": [71], "model": [74], "RTX": [76], "3080": [77], "Ti": [78], "of": [79], "16GB": [80], "achieves": [83], "comparable": [84], "or": [85], "better": [86], "benchmarks": [91], "than": [92], "several": [94], "times": [95], "larger,": [96], "resource-constrained": [98], "environments.": [99], "Our": [100], "results": [101], "challenge": [102], "the": [103], "paradigm": [104], "state-of-the-art": [106], "necessitates": [109], "massive": [110], "infrastructure,": [111], "democratizing": [112], "access": [113], "to": [114], "high-performance": [115], "AI": [116], "research.": [117], "https://github.com/shinandrew/YouronMath.": [118]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.3303000032901764, "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": 0.3303000032901764, "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/T13523", "display_name": "Mathematics, Computing, and Information Processing", "score": 0.16279999911785126, "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/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.13439999520778656, "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:2506.08935", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.08935", "pdf_url": "https://arxiv.org/pdf/2506.08935", "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/W4416075235", "doi": "https://doi.org/10.48550/arxiv.2506.04207", "title": "Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning", "publication_year": 2025, "publication_date": "2025-06-04", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100443515", "display_name": "Shuang Chen", "orcid": "https://orcid.org/0000-0003-4504-7470", "observed_orcids": ["https://orcid.org/0000-0003-4504-7470"]}, "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": "Chen, Shuang", "raw_affiliation_strings": ["Zhejiang University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhejiang University", "institution_ids": ["https://openalex.org/I76130692"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Guo, Yue", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I24943067", "display_name": "Fudan University", "ror": "https://ror.org/013q1eq08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24943067"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Guo, Yue", "raw_affiliation_strings": ["Fudan University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Fudan University", "institution_ids": ["https://openalex.org/I24943067"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5084648899", "display_name": "Zhaochen Su", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I3923682", "display_name": "Soochow University", "ror": "https://ror.org/05t8y2r12", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I3923682"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Su, Zhaochen", "raw_affiliation_strings": ["Soochow University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Soochow University", "institution_ids": ["https://openalex.org/I3923682"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5032649444", "display_name": "Yafu Li", "orcid": "https://orcid.org/0000-0002-7895-9997", "observed_orcids": ["https://orcid.org/0000-0002-7895-9997"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Li, Yafu", "raw_affiliation_strings": ["Shanghai AI Laboratory"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5054513117", "display_name": "Yulun Wu", "orcid": "https://orcid.org/0000-0003-1352-5749", "observed_orcids": ["https://orcid.org/0000-0003-1352-5749"]}, "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": "Wu, Yulun", "raw_affiliation_strings": ["Zhejiang University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhejiang University", "institution_ids": ["https://openalex.org/I76130692"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5073290151", "display_name": "Jiacheng Chen", "orcid": "https://orcid.org/0000-0001-9251-0670", "observed_orcids": ["https://orcid.org/0000-0001-9251-0670"]}, "institutions": [{"id": "https://openalex.org/I24943067", "display_name": "Fudan University", "ror": "https://ror.org/013q1eq08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24943067"]}, {"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chen, Jiacheng", "raw_affiliation_strings": ["Fudan University", "Shanghai AI Laboratory"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Fudan University", "institution_ids": ["https://openalex.org/I24943067"]}, {"raw_affiliation_string": "Shanghai AI Laboratory", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039200963", "display_name": "Jiayu Chen", "orcid": "https://orcid.org/0009-0009-2372-4654", "observed_orcids": ["https://orcid.org/0009-0009-2372-4654"]}, "institutions": [{"id": "https://openalex.org/I24943067", "display_name": "Fudan University", "ror": "https://ror.org/013q1eq08", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24943067"]}, {"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chen, Jiayu", "raw_affiliation_strings": ["Fudan University", "Shanghai AI Laboratory"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Fudan University", "institution_ids": ["https://openalex.org/I24943067"]}, {"raw_affiliation_string": "Shanghai AI Laboratory", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5030917100", "display_name": "Weijie Wang", "orcid": "https://orcid.org/0009-0006-8467-2577", "observed_orcids": ["https://orcid.org/0009-0006-8467-2577"]}, "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": "Wang, Weijie", "raw_affiliation_strings": ["Zhejiang University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhejiang University", "institution_ids": ["https://openalex.org/I76130692"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065871371", "display_name": "Xiaoye Qu", "orcid": "https://orcid.org/0000-0002-4907-3978", "observed_orcids": ["https://orcid.org/0000-0002-4907-3978"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Qu, Xiaoye", "raw_affiliation_strings": ["Shanghai AI Laboratory"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5038726410", "display_name": "Yu Qing Cheng", "orcid": "https://orcid.org/0009-0001-1570-425X", "observed_orcids": ["https://orcid.org/0009-0001-1570-425X"]}, "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": "Cheng, Yu", "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"]}]}], "abstract_inverted_index": {"Inspired": [0], "by": [1, 25], "the": [2, 119, 141], "remarkable": [3], "reasoning": [4, 90, 137], "capabilities": [5, 18], "of": [6], "Deepseek-R1": [7], "in": [8, 19, 47], "complex": [9, 37], "textual": [10], "tasks,": [11], "many": [12, 87], "works": [13], "attempt": [14], "to": [15, 35, 84, 100], "incentivize": [16], "similar": [17], "Multimodal": [20], "Large": [21], "Language": [22], "Models": [23], "(MLLMs)": [24], "directly": [26], "applying": [27], "reinforcement": [28], "learning": [29], "(RL).": [30], "However,": [31], "they": [32], "still": [33], "struggle": [34], "activate": [36], "reasoning.": [38, 70, 126], "In": [39], "this": [40], "paper,": [41], "rather": [42], "than": [43], "examining": [44], "multimodal": [45, 89, 94, 101, 120, 125, 146], "RL": [46, 102, 116, 121, 147], "isolation,": [48], "we": [49, 72, 149], "delve": [50], "into": [51], "current": [52], "training": [53, 109, 129], "pipelines": [54], "and": [55, 111, 135, 144, 169, 172], "identify": [56], "three": [57], "crucial": [58], "phenomena:": [59], "1)": [60], "Effective": [61], "cold": [62], "start": [63], "initialization": [64], "is": [65], "critical": [66], "for": [67], "enhancing": [68], "MLLM": [69], "Intriguingly,": [71], "find": [73], "that": [74], "initializing": [75], "with": [76], "carefully": [77], "selected": [78], "text": [79], "data": [80], "alone": [81], "can": [82], "lead": [83], "performance": [85], "surpassing": [86], "recent": [88], "models,": [91], "even": [92], "before": [93], "RL.": [95], "2)": [96], "Standard": [97], "GRPO": [98], "applied": [99], "suffers": [103], "from": [104], "gradient": [105], "stagnation,": [106], "which": [107], "degrades": [108], "stability": [110], "performance.": [112], "3)": [113], "Subsequent": [114], "text-only": [115], "training,": [117], "following": [118], "phase,": [122], "further": [123], "enhances": [124], "This": [127], "staged": [128], "approach": [130], "effectively": [131], "balances": [132], "perceptual": [133], "grounding": [134], "cognitive": [136], "development.": [138], "By": [139], "incorporating": [140], "above": [142], "insights": [143], "addressing": [145], "issues,": [148], "introduce": [150], "ReVisual-R1,": [151], "achieving": [152], "a": [153], "new": [154], "state-of-the-art": [155], "among": [156], "open-source": [157], "7B": [158], "MLLMs": [159], "on": [160], "challenging": [161, 170], "benchmarks": [162], "including": [163], "MathVerse,": [164], "MathVision,": [165], "WeMath,": [166], "LogicVista,": [167], "DynaMath,": [168], "AIME2024": [171], "AIME2025.": [173]}, "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/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"}}, {"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:2506.04207", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.04207", "pdf_url": "https://arxiv.org/pdf/2506.04207", "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/W4414756304", "doi": "https://doi.org/10.48550/arxiv.2509.06169", "title": "Reasoning Language Model for Personalized Lung Cancer Screening", "publication_year": 2025, "publication_date": "2025-09-07", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5065193592", "display_name": "Chuang Niu", "orcid": "https://orcid.org/0000-0002-3310-7803", "observed_orcids": ["https://orcid.org/0000-0002-3310-7803"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Niu, Chuang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100400458", "display_name": "Ge Wang", "orcid": "https://orcid.org/0000-0002-2656-7705", "observed_orcids": ["https://orcid.org/0000-0002-2656-7705"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Ge", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Accurate": [0], "risk": [1, 52, 62, 84, 108, 124, 134, 142], "assessment": [2], "in": [3, 107, 113], "lung": [4, 56, 82, 116, 170], "cancer": [5, 12, 83, 171], "screening": [6, 117], "is": [7], "critical": [8], "for": [9, 36, 80], "enabling": [10], "early": [11], "detection": [13], "and": [14, 24, 39, 47, 93, 99, 136, 156], "minimizing": [15], "unnecessary": [16], "invasive": [17], "procedures.": [18], "The": [19], "Lung": [20], "CT": [21], "Screening": [22], "Reporting": [23], "Data": [25], "System": [26], "(Lung-RADS)": [27], "has": [28], "been": [29], "widely": [30], "used": [31], "as": [32, 49], "the": [33, 114, 123, 130, 159], "standard": [34], "framework": [35], "patient": [37], "management": [38], "follow-up.": [40], "Nevertheless,": [41], "Lung-RADS": [42], "faces": [43], "trade-offs": [44], "between": [45], "sensitivity": [46], "specificity,": [48], "it": [50], "stratifies": [51], "solely": [53], "based": [54], "on": [55, 111], "nodule": [57], "characteristics": [58], "without": [59], "incorporating": [60], "various": [61], "factors.": [63], "Here": [64], "we": [65], "propose": [66], "a": [67, 87, 140], "reasoning": [68, 163], "language": [69], "model": [70, 103], "(RLM)": [71], "to": [72], "integrate": [73], "radiology": [74], "findings": [75], "with": [76], "longitudinal": [77], "medical": [78], "records": [79], "individualized": [81], "assessment.": [85], "Through": [86], "systematic": [88], "study": [89], "including": [90], "dataset": [91], "construction": [92], "distillation,": [94], "supervised": [95], "fine-tuning,": [96], "reinforcement": [97], "learning,": [98], "comprehensive": [100], "evaluation,": [101], "our": [102, 146], "makes": [104], "significant": [105], "improvements": [106], "prediction": [109], "performance": [110], "datasets": [112], "national": [115], "trial.": [118], "Notably,": [119], "RLM": [120], "can": [121], "decompose": [122], "evaluation": [125], "task": [126], "into": [127, 139, 169], "sub-components,": [128], "analyze": [129], "contributions": [131], "of": [132, 161], "diverse": [133], "factors,": [135], "synthesize": [137], "them": [138], "final": [141], "score": [143], "computed": [144], "using": [145], "data-driven": [147], "system": [148], "equation.": [149], "Our": [150], "approach": [151], "improves": [152], "both": [153], "predictive": [154], "accuracy": [155], "monitorability": [157], "through": [158], "chain": [160], "thought": [162], "process,": [164], "thereby": [165], "facilitating": [166], "clinical": [167], "translation": [168], "screening.": [172]}, "primary_topic": {"id": "https://openalex.org/T10202", "display_name": "Lung Cancer Diagnosis and Treatment", "score": 0.5565999746322632, "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"}}, "topics": [{"id": "https://openalex.org/T10202", "display_name": "Lung Cancer Diagnosis and Treatment", "score": 0.5565999746322632, "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/T10862", "display_name": "AI in cancer detection", "score": 0.29269999265670776, "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/T12422", "display_name": "Radiomics and Machine Learning in Medical Imaging", "score": 0.06830000132322311, "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": "pmh:oai:arXiv.org:2509.06169", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2509.06169", "pdf_url": "https://arxiv.org/pdf/2509.06169", "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/W4416174161", "doi": "https://doi.org/10.48550/arxiv.2504.16832", "title": "GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning", "publication_year": 2025, "publication_date": "2025-04-23", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5112668223", "display_name": "Le Quoc Thang Thai Thanh Tung", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tung, Luu Quy", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103586951", "display_name": "Hoang Quoc Viet", "orcid": "https://orcid.org/0009-0005-5918-8903", "observed_orcids": ["https://orcid.org/0009-0005-5918-8903"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Viet, Hoang Quoc", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120647832", "display_name": "Pham Bao Loc", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Loc, Pham Bao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5120445471", "display_name": "Vo Trong Thu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Thu, Vo Trong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Chain-of-Thought": [0], "(CoT)": [1], "is": [2], "a": [3, 18, 45], "robust": [4], "approach": [5], "for": [6], "tackling": [7], "LLM": [8], "tasks": [9], "that": [10, 92, 119], "require": [11], "intermediate": [12], "reasoning": [13, 29, 49, 95, 147], "steps": [14], "prior": [15, 123], "to": [16, 56, 90, 137, 150], "generating": [17], "final": [19, 105], "answer.": [20], "In": [21], "this": [22, 62], "paper,": [23], "we": [24, 68, 85, 133], "present": [25], "GreenMind-Medium-14B-R1,": [26], "the": [27, 33, 58, 71, 78, 93, 104, 110, 114, 143], "Vietnamese": [28, 47, 111], "model": [30, 121], "inspired": [31], "by": [32], "finetuning": [34], "strategy": [35], "based": [36], "on": [37, 109], "Group": [38], "Relative": [39], "Policy": [40], "Optimization.": [41], "We": [42], "also": [43], "leverage": [44, 86], "high-quality": [46], "synthesized": [48], "dataset": [50, 112], "and": [51, 83, 100, 125], "design": [52], "two": [53], "reward": [54], "functions": [55], "tackle": [57], "main": [59], "limitations": [60], "of": [61, 73, 80, 145], "technique:": [63], "(i)": [64], "language": [65, 75], "mixing,": [66], "where": [67], "explicitly": [69], "detect": [70], "presence": [72], "biased": [74], "characters": [76], "during": [77], "process": [79], "sampling": [81], "tokens,": [82], "(ii)": [84], "Sentence": [87], "Transformer-based": [88], "models": [89], "ensure": [91], "generated": [94], "content": [96], "maintains": [97], "factual": [98], "correctness": [99], "does": [101], "not": [102], "distort": [103], "output.": [106], "Experimental": [107], "results": [108], "from": [113], "VLSP": [115], "2023": [116], "Challenge": [117], "demonstrate": [118], "our": [120, 135, 146], "outperforms": [122], "works": [124], "enhances": [126], "linguistic": [127], "consistency": [128], "in": [129], "its": [130], "responses.": [131], "Furthermore,": [132], "extend": [134], "evaluation": [136], "SeaExam-a": [138], "multilingual": [139], "multiple-choice": [140], "dataset,": [141], "showing": [142], "effectiveness": [144], "method": [148], "compared": [149], "few-shot": [151], "prompting": [152], "techniques.": [153]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9336000084877014, "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": 0.9336000084877014, "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": 0.053199999034404755, "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": 0.007300000172108412, "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:2504.16832", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.16832", "pdf_url": "https://arxiv.org/pdf/2504.16832", "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/W4417163150", "doi": "https://doi.org/10.48550/arxiv.2508.01016", "title": "Diagnostic Accuracy of Open-Source Vision-Language Models on Diverse Medical Imaging Tasks", "publication_year": 2025, "publication_date": "2025-08-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5055585858", "display_name": "Gustav Anton M\u00fcller\u2010Franzes", "orcid": "https://orcid.org/0000-0002-7413-2570", "observed_orcids": ["https://orcid.org/0000-0002-7413-2570"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "M\u00fcller-Franzes, Gustav", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119876381", "display_name": "Debora Jutz", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jutz, Debora", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113262662", "display_name": "Jakob Nikolas Kather", "orcid": "https://orcid.org/0000-0002-3730-5348", "observed_orcids": ["https://orcid.org/0000-0002-3730-5348"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kather, Jakob Nikolas", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5070612619", "display_name": "Christiane Katharina Kuhl", "orcid": "https://orcid.org/0000-0001-8696-2363", "observed_orcids": ["https://orcid.org/0000-0001-8696-2363"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kuhl, Christiane", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091689170", "display_name": "Sven Nebelung", "orcid": "https://orcid.org/0000-0002-5267-9962", "observed_orcids": ["https://orcid.org/0000-0002-5267-9962"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nebelung, Sven", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5016512818", "display_name": "Daniel Truhn", "orcid": "https://orcid.org/0000-0002-9605-0728", "observed_orcids": ["https://orcid.org/0000-0002-9605-0728"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Truhn, Daniel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"This": [0, 16], "retrospective": [1], "study": [2], "evaluated": [3], "five": [4], "VLMs": [5, 119, 188], "(Qwen2.5,": [6], "Phi-4,": [7], "Gemma3,": [8], "Llama3.2,": [9], "and": [10, 46, 66, 94, 109, 128, 148, 175, 177, 215], "Mistral3.1)": [11], "using": [12, 80], "the": [13, 87, 100, 151, 210], "MedFMC": [14], "dataset.": [15], "dataset": [17], "includes": [18], "22,349": [19], "images": [20, 96], "from": [21], "7,461": [22], "patients": [23], "encompassing": [24], "chest": [25, 91, 195], "radiography": [26], "(19": [27], "disease": [28], "multi-label": [29], "classifications),": [30], "colon": [31, 105], "pathology": [32], "(tumor": [33], "detection),": [34], "endoscopy": [35, 95], "(colorectal": [36], "lesion": [37], "identification),": [38], "neonatal": [39, 123], "jaundice": [40, 124], "assessment": [41], "(skin": [42], "color-based": [43], "treatment": [44], "necessity),": [45], "retinal": [47, 145, 205], "fundoscopy": [48, 206], "(5-point": [49], "diabetic": [50], "retinopathy": [51], "grading).": [52], "Diagnostic": [53], "accuracy": [54, 70, 89, 171], "was": [55, 71, 207], "compared": [56], "in": [57, 194, 200], "three": [58], "experimental": [59], "settings:": [60], "visual": [61], "input": [62, 169], "only,": [63], "multimodal": [64, 168], "input,": [65], "chain-of-thought": [67, 178], "reasoning.": [68], "Model": [69], "assessed": [72], "against": [73], "ground": [74], "truth": [75], "labels,": [76], "with": [77, 144], "statistical": [78], "comparisons": [79], "bootstrapped": [81], "confidence": [82], "intervals": [83], "(p<.05).": [84], "Qwen2.5": [85, 107, 126, 147], "achieved": [86, 150], "highest": [88], "for": [90, 122, 172, 212], "radiographs": [92], "(90.4%)": [93], "(84.2%),": [97], "significantly": [98, 116, 136, 160], "outperforming": [99], "other": [101, 118, 163], "models": [102, 142, 165, 174], "(p<.001).": [103, 120, 140, 166], "In": [104], "pathology,": [106], "(69.0%)": [108], "Phi-4": [110, 129], "(69.6%)": [111], "performed": [112], "comparably": [113], "(p=.41),": [114], "both": [115], "exceeding": [117, 137], "Similarly,": [121], "assessment,": [125], "(58.3%)": [127], "(58.1%)": [130], "showed": [131], "comparable": [132], "leading": [133], "accuracies": [134, 155], "(p=.93)": [135], "their": [138], "counterparts": [139], "All": [141], "struggled": [143], "fundoscopy;": [146], "Gemma3": [149], "highest,": [152], "albeit": [153], "modest,": [154], "at": [156], "18.6%": [157], "(comparable,": [158], "p=.99),": [159], "better": [161], "than": [162], "tested": [164], "Unexpectedly,": [167], "reduced": [170], "some": [173], "modalities,": [176], "reasoning": [179], "prompts": [180], "also": [181], "failed": [182], "to": [183], "improve": [184], "accuracy.": [185], "The": [186], "open-source": [187], "demonstrated": [189], "promising": [190], "diagnostic": [191], "capabilities,": [192], "particularly": [193], "radiograph": [196], "interpretation.": [197], "However,": [198], "performance": [199], "complex": [201], "domains": [202], "such": [203], "as": [204], "limited,": [208], "underscoring": [209], "need": [211], "further": [213], "development": [214], "domain-specific": [216], "adaptation": [217], "before": [218], "widespread": [219], "clinical": [220], "application.": [221]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.6015999913215637, "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": 0.6015999913215637, "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/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.37940001487731934, "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/T10862", "display_name": "AI in cancer detection", "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"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2508.01016", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2508.01016", "pdf_url": "https://arxiv.org/pdf/2508.01016", "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/W4413189005", "doi": "https://doi.org/10.3390/sym17081303", "title": "Dynamic Asymmetric Attention for Enhanced Reasoning and Interpretability in LLMs", "publication_year": 2025, "publication_date": "2025-08-12", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073348223", "display_name": "Feng Wen", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210113703", "display_name": "Henan University of Urban Construction", "ror": "https://ror.org/01x1skr92", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I4210113703"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Feng Wen", "raw_affiliation_strings": ["School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China", "institution_ids": ["https://openalex.org/I4210113703"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065697638", "display_name": "Xiaoming Lu", "orcid": "https://orcid.org/0000-0002-0830-2826", "observed_orcids": ["https://orcid.org/0000-0002-0830-2826"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xiaoming Lu", "raw_affiliation_strings": ["The Scientific Academy of Land and Resource of Henan Province, Zhengzhou 467300, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Scientific Academy of Land and Resource of Henan Province, Zhengzhou 467300, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5111230347", "display_name": "Haikun Yu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Haikun Yu", "raw_affiliation_strings": ["Henan Remote Sensing Institute, Henan Provincial Science and Technology Innovation Center for Natural Resources (Satellite Remote Sensing Research), Zhengzhou 467300, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Henan Remote Sensing Institute, Henan Provincial Science and Technology Innovation Center for Natural Resources (Satellite Remote Sensing Research), Zhengzhou 467300, China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102990000", "display_name": "Chunyang Lu", "orcid": "https://orcid.org/0009-0001-4601-3435", "observed_orcids": ["https://orcid.org/0009-0001-4601-3435"]}, "institutions": [{"id": "https://openalex.org/I4210113703", "display_name": "Henan University of Urban Construction", "ror": "https://ror.org/01x1skr92", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I4210113703"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Chunyang Lu", "raw_affiliation_strings": ["School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China", "institution_ids": ["https://openalex.org/I4210113703"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100615008", "display_name": "Huijie Li", "orcid": "https://orcid.org/0000-0002-8304-5241", "observed_orcids": ["https://orcid.org/0000-0002-8304-5241"]}, "institutions": [{"id": "https://openalex.org/I4210113703", "display_name": "Henan University of Urban Construction", "ror": "https://ror.org/01x1skr92", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I4210113703"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Huijie Li", "raw_affiliation_strings": ["School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan 467036, China", "institution_ids": ["https://openalex.org/I4210113703"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5010080018", "display_name": "Xiayang Shi", "orcid": "https://orcid.org/0000-0003-1539-712X", "observed_orcids": ["https://orcid.org/0000-0003-1539-712X"]}, "institutions": [{"id": "https://openalex.org/I23171815", "display_name": "Zhengzhou University of Light Industry", "ror": "https://ror.org/05fwr8z16", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I23171815"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Xiayang Shi", "raw_affiliation_strings": ["College of Software, Zhengzhou University of Light Industry, Zhengzhou 450000, China"], "raw_orcid": "https://orcid.org/0000-0003-1539-712X", "affiliations": [{"raw_affiliation_string": "College of Software, Zhengzhou University of Light Industry, Zhengzhou 450000, China", "institution_ids": ["https://openalex.org/I23171815"]}]}], "abstract_inverted_index": {"The": [0], "remarkable": [1], "success": [2], "of": [3, 23, 130, 241], "autoregressive": [4], "Large": [5], "Language": [6], "Models": [7], "(LLMs)": [8], "is": [9, 173], "predicated": [10], "on": [11, 127, 136, 143], "the": [12, 48, 81, 115, 167, 177, 183, 192, 235], "causal": [13, 83], "attention": [14, 96, 170], "mechanism,": [15], "which": [16], "enforces": [17], "a": [18, 76, 86, 94, 104, 128, 159, 217, 222, 238], "static": [19, 82, 218], "and": [20, 52, 61, 139, 152, 197, 224, 244], "rigid": [21], "form": [22], "informational": [24], "asymmetry": [25, 220], "by": [26, 70], "permitting": [27], "each": [28, 99], "token": [29], "to": [30, 33, 46, 175, 221], "attend": [31], "only": [32, 228], "its": [34, 206], "predecessors.": [35], "While": [36], "effective": [37], "for": [38, 98, 162, 237], "sequential": [39], "generation,": [40], "this": [41, 64, 68], "hard-coded": [42], "unidirectional": [43], "constraint": [44], "fails": [45], "capture": [47], "more": [49, 209, 242, 246], "complex,": [50], "dynamic,": [51], "nonlinear": [53], "dependencies": [54], "inherent": [55], "in": [56, 134, 202], "sophisticated": [57], "reasoning,": [58, 204], "logical": [59, 200], "inference,": [60], "discourse.": [62], "In": [63], "paper,": [65], "we": [66], "challenge": [67], "paradigm": [69], "introducing": [71], "Dynamic": [72], "Asymmetric": [73], "Attention": [74], "(DAA),": [75], "novel": [77], "mechanism": [78], "that": [79, 109, 182, 214], "replaces": [80], "mask": [84], "with": [85], "learnable": [87], "context-aware": [88], "guidance": [89], "module.": [90], "DAA": [91, 157], "dynamically": [92, 194], "generates": [93], "continuous-valued": [95], "bias": [97], "query\u2013key": [100], "pair,": [101], "effectively": [102], "learning": [103], "\u201csoft\u201d": [105], "information": [106, 179], "flow": [107, 180], "policy": [108], "guides": [110], "rather": [111], "than": [112], "merely": [113], "restricts": [114], "model\u2019s": [116], "focus.": [117], "Trained": [118], "end-to-end,": [119], "our": [120], "DAA-augmented": [121], "models": [122], "demonstrate": [123], "significant": [124], "performance": [125, 231], "gains": [126], "suite": [129], "benchmarks,": [131], "including": [132], "improvements": [133], "perplexity": [135], "language": [137], "modeling": [138], "notable": [140], "accuracy": [141], "boosts": [142], "complex": [144], "reasoning": [145], "tasks": [146], "such": [147], "as": [148], "code": [149], "generation": [150], "(HumanEval)": [151], "mathematical": [153], "problem-solving": [154], "(GSM8k).": [155], "Crucially,": [156], "provides": [158], "new": [160, 239], "lens": [161], "model": [163, 184, 193, 230], "interpretability.": [164], "By": [165], "visualizing": [166], "learned": [168, 223], "asymmetric": [169], "patterns,": [171], "it": [172], "possible": [174], "uncover": [176], "implicit": [178], "graphs": [181], "constructs": [185], "during": [186], "inference.": [187], "These": [188], "visualizations": [189], "reveal": [190], "how": [191], "prioritizes": [195], "evidence": [196], "forges": [198], "directed": [199], "links": [201], "chain-of-thought": [203], "making": [205], "decision-making": [207], "process": [208], "transparent.": [210], "Our": [211], "work": [212], "demonstrates": [213], "transitioning": [215], "from": [216], "hard-wired": [219], "dynamic": [225], "one": [226], "not": [227], "enhances": [229], "but": [232], "also": [233], "paves": [234], "way": [236], "class": [240], "capable": [243], "profoundly": [245], "explainable": [247], "LLMs.": [248]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.923799991607666, "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": 0.923799991607666, "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": 0.03959999978542328, "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": 0.013799999840557575, "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:10.3390/sym17081303", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/sym17081303", "pdf_url": "https://www.mdpi.com/2073-8994/17/8/1303/pdf", "source": {"id": "https://openalex.org/S190787756", "display_name": "Symmetry", "issn_l": "2073-8994", "issn": ["2073-8994"], "is_oa": true, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "norway-1"], "host_organization": "https://openalex.org/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Symmetry", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4411710498", "doi": "https://doi.org/10.3390/app15137159", "title": "Multi-Agent Framework Utilizing Large Language Models for Solving Capture-the-Flag Challenges in Cybersecurity Competitions", "publication_year": 2025, "publication_date": "2025-06-25", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102121982", "display_name": "Zewen Huang", "orcid": "https://orcid.org/0009-0007-8035-6945", "observed_orcids": ["https://orcid.org/0009-0007-8035-6945"]}, "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": "Zewen Huang", "raw_affiliation_strings": ["Weiyang College, Tsinghua University, Beijing 100084, China"], "raw_orcid": "https://orcid.org/0009-0007-8035-6945", "affiliations": [{"raw_affiliation_string": "Weiyang College, Tsinghua University, Beijing 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5118658611", "display_name": "Jinjing Zhuge", "orcid": "https://orcid.org/0009-0007-1748-1954", "observed_orcids": ["https://orcid.org/0009-0007-1748-1954"]}, "institutions": [{"id": "https://openalex.org/I47720641", "display_name": "Huazhong University of Science and Technology", "ror": "https://ror.org/00p991c53", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I47720641"]}, {"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": "Jinjing Zhuge", "raw_affiliation_strings": ["Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China"], "raw_orcid": "https://orcid.org/0009-0007-1748-1954", "affiliations": [{"raw_affiliation_string": "Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}, {"raw_affiliation_string": "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China", "institution_ids": ["https://openalex.org/I47720641"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Jinjing Zhuge", "orcid": "https://orcid.org/0009-0007-1748-1954", "observed_orcids": ["https://orcid.org/0009-0007-1748-1954"]}, "institutions": [{"id": "https://openalex.org/I47720641", "display_name": "Huazhong University of Science and Technology", "ror": "https://ror.org/00p991c53", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I47720641"]}, {"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": "Jinjing Zhuge", "raw_affiliation_strings": ["Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China"], "raw_orcid": "https://orcid.org/0009-0007-1748-1954", "affiliations": [{"raw_affiliation_string": "Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}, {"raw_affiliation_string": "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China", "institution_ids": ["https://openalex.org/I47720641"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Jianwei Zhuge", "orcid": "https://orcid.org/0009-0005-9570-3335", "observed_orcids": ["https://orcid.org/0009-0005-9570-3335"]}, "institutions": [{"id": "https://openalex.org/I47720641", "display_name": "Huazhong University of Science and Technology", "ror": "https://ror.org/00p991c53", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I47720641"]}, {"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": "Jianwei Zhuge", "raw_affiliation_strings": ["Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China"], "raw_orcid": "https://orcid.org/0009-0005-9570-3335", "affiliations": [{"raw_affiliation_string": "Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}, {"raw_affiliation_string": "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China", "institution_ids": ["https://openalex.org/I47720641"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Jianwei Zhuge", "orcid": "https://orcid.org/0009-0005-9570-3335", "observed_orcids": ["https://orcid.org/0009-0005-9570-3335"]}, "institutions": [{"id": "https://openalex.org/I47720641", "display_name": "Huazhong University of Science and Technology", "ror": "https://ror.org/00p991c53", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I47720641"]}, {"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": "Jianwei Zhuge", "raw_affiliation_strings": ["Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China"], "raw_orcid": "https://orcid.org/0009-0005-9570-3335", "affiliations": [{"raw_affiliation_string": "Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing 100084, China", "institution_ids": ["https://openalex.org/I99065089"]}, {"raw_affiliation_string": "School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China", "institution_ids": ["https://openalex.org/I47720641"]}]}], "abstract_inverted_index": {"Capture": [0], "the": [1, 37, 51, 63, 73, 83, 115, 118, 122, 125, 138, 155, 165], "Flag": [2], "(CTF)": [3], "is": [4], "an": [5], "important": [6], "form": [7], "of": [8, 39, 53, 69, 75, 82, 167], "competition": [9], "in": [10, 44, 72, 121, 161], "cybersecurity,": [11], "which": [12], "tests": [13], "participants\u2019": [14], "knowledge": [15], "and": [16, 33, 46, 57, 89, 95, 124, 140, 164], "problem-solving": [17, 99], "abilities.": [18], "We": [19, 49, 77, 109, 152], "propose": [20], "a": [21, 66, 111], "multi-agent": [22], "framework": [23], "based": [24, 113], "on": [25, 114, 137], "large": [26, 84], "language": [27, 64, 158], "models": [28, 159], "to": [29, 35, 61, 86, 92, 96], "simulate": [30], "human": [31, 146], "participants": [32], "attempt": [34], "automate": [36], "solutions": [38, 91], "common": [40], "CTF": [41, 93], "problems,": [42, 94], "especially": [43], "cryptographic": [45], "miscellaneous": [47], "challenges.": [48], "implement": [50], "collaboration": [52], "multiple": [54], "expert": [55], "agents": [56, 134], "access": [58], "external": [59, 107], "tools": [60], "give": [62], "model": [65], "basic": [67], "level": [68], "practical": [70], "competence": [71], "field": [74], "cybersecurity.": [76], "primarily": [78], "test": [79], "two": [80], "capabilities": [81], "model:": [85], "analyze,": [87], "reason,": [88], "determine": [90], "assist": [97], "with": [98, 144, 149], "by": [100], "generating": [101], "code": [102], "or": [103], "utilizing": [104], "unannotated": [105], "existing": [106], "tools.": [108], "construct": [110], "benchmark": [112], "puzzles": [116], "from": [117], "book": [119], "\u201cGhost": [120], "Wires\u201d": [123], "THUCTF": [126], "competition.": [127], "The": [128], "experiment": [129], "results": [130], "showed": [131], "that": [132, 157], "our": [133], "performed": [135], "well": [136], "former": [139], "were": [141], "significantly": [142], "improved": [143], "some": [145], "hints,": [147], "compared": [148], "related": [150], "work.": [151], "also": [153], "discuss": [154], "challenges": [156, 163], "face": [160], "cybersecurity": [162], "effect": [166], "leveraging": [168], "reasoning": [169], "models.": [170]}, "primary_topic": {"id": "https://openalex.org/T10734", "display_name": "Information and Cyber Security", "score": 0.3334999978542328, "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/T10734", "display_name": "Information and Cyber Security", "score": 0.3334999978542328, "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/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 0.1914999932050705, "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": 0.07530000060796738, "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:10.3390/app15137159", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/app15137159", "pdf_url": "https://www.mdpi.com/2076-3417/15/13/7159/pdf?version=1750921026", "source": {"id": "https://openalex.org/S4210205812", "display_name": "Applied Sciences", "issn_l": "2076-3417", "issn": ["2076-3417"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "norway-1"], "host_organization": "https://openalex.org/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "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 Sciences", "raw_type": "journal-article"}, "cited_by_count": 3, "is_retracted": false}, {"id": "https://openalex.org/W4416667336", "doi": "https://doi.org/10.48550/arxiv.2511.16940", "title": "MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models", "publication_year": 2025, "publication_date": "2025-11-21", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101976747", "display_name": "Xiongtao Sun", "orcid": "https://orcid.org/0000-0001-9264-0766", "observed_orcids": ["https://orcid.org/0000-0001-9264-0766"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Xiongtao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100712362", "display_name": "Hui Li", "orcid": "https://orcid.org/0000-0002-3800-5435", "observed_orcids": ["https://orcid.org/0000-0002-3800-5435"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Hui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100453768", "display_name": "Jiaming Zhang", "orcid": "https://orcid.org/0000-0001-9146-0501", "observed_orcids": ["https://orcid.org/0000-0001-9146-0501"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Jiaming", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101620890", "display_name": "Yujie Yang", "orcid": "https://orcid.org/0009-0007-6262-6358", "observed_orcids": ["https://orcid.org/0009-0007-6262-6358", "https://orcid.org/0000-0002-2958-990X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Yujie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101944547", "display_name": "Kaili Liu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Kaili", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Feng, Ruxin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Feng, Ruxin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5080332038", "display_name": "Wen Jun Tan", "orcid": "https://orcid.org/0000-0003-2204-0639", "observed_orcids": ["https://orcid.org/0000-0003-2204-0639"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tan, Wen Jun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5027969322", "display_name": "Wei Yang Bryan Lim", "orcid": "https://orcid.org/0000-0003-2150-5561", "observed_orcids": ["https://orcid.org/0000-0003-2150-5561"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lim, Wei Yang Bryan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Modern": [0], "Vision-Language": [1], "Models": [2], "(VLMs)": [3], "pose": [4], "significant": [5, 158], "individual-level": [6, 75, 148], "privacy": [7, 23, 35, 46, 76, 149], "risks": [8], "by": [9], "linking": [10], "fragmented": [11], "multimodal": [12, 93], "data": [13], "to": [14, 39, 51, 57, 72, 108, 153, 161], "identifiable": [15], "individuals": [16], "through": [17], "hierarchical": [18], "chain-of-thought": [19], "reasoning.": [20], "However,": [21], "existing": [22], "benchmarks": [24], "remain": [25], "structurally": [26], "insufficient": [27], "for": [28], "this": [29, 63], "threat,": [30], "as": [31, 102], "they": [32], "primarily": [33], "evaluate": [34, 74], "perception": [36], "while": [37], "failing": [38], "address": [40, 62], "the": [41, 68, 82], "more": [42], "critical": [43], "risk": [44], "of": [45, 130, 142], "reasoning:": [47], "a": [48, 91, 127, 157], "VLM's": [49], "ability": [50], "infer": [52], "and": [53, 85, 89, 104, 122, 134], "link": [54], "distributed": [55], "information": [56], "construct": [58, 90], "individual": [59, 97], "profiles.": [60], "To": [61], "gap,": [64], "we": [65], "propose": [66], "MultiPriv,": [67], "first": [69], "benchmark": [70, 165], "designed": [71], "systematically": [73], "reasoning": [77, 150], "in": [78], "VLMs.": [79, 136], "We": [80, 125], "introduce": [81], "Privacy": [83], "Perception": [84], "Reasoning": [86], "(PPR)": [87], "framework": [88], "bilingual": [92], "dataset": [94], "with": [95, 151], "synthetic": [96], "profiles,": [98], "where": [99], "identifiers,": [100], "such": [101], "faces": [103], "names,": [105], "are": [106], "linked": [107], "sensitive": [109], "attributes.": [110], "This": [111], "design": [112], "enables": [113], "nine": [114], "challenging": [115], "tasks": [116], "spanning": [117], "attribute": [118], "detection,": [119], "cross-image": [120], "re-identification,": [121], "chained": [123], "inference.": [124], "conduct": [126], "large-scale": [128], "evaluation": [129], "over": [131], "50": [132], "open-source": [133], "commercial": [135], "In": [137], "our": [138], "controlled": [139], "benchmark,": [140], "60%": [141], "widely": [143], "used": [144], "VLMs": [145], "can": [146], "perform": [147], "up": [152], "80%": [154], "accuracy,": [155], "suggesting": [156], "potential": [159], "threat": [160], "personal": [162], "privacy.": [163], "The": [164], "is": [166], "available": [167], "at": [168], "https://github.com/CyberChangAn/MultiPriv-PII.": [169]}, "primary_topic": {"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9589999914169312, "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": 0.9589999914169312, "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/T11045", "display_name": "Privacy, Security, and Data Protection", "score": 0.023000000044703484, "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": 0.0038999998942017555, "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:2511.16940", "is_oa": true, "landing_page_url": "https://arxiv.org/abs/2511.16940", "pdf_url": "https://arxiv.org/pdf/2511.16940", "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/W7117130051", "doi": "https://doi.org/10.3390/ijgi15010008", "title": "Domain-Adapted MLLMs for Interpretable Road Traffic Accident Analysis Using Remote Sensing Imagery", "publication_year": 2025, "publication_date": "2025-12-21", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5113347971", "display_name": "Bing He", "orcid": "https://orcid.org/0009-0002-2510-7069", "observed_orcids": ["https://orcid.org/0009-0002-2510-7069"]}, "institutions": [{"id": "https://openalex.org/I24201400", "display_name": "Chengdu University of Information Technology", "ror": "https://ror.org/01yxwrh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24201400"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Bing He", "raw_affiliation_strings": ["School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China"], "raw_orcid": "https://orcid.org/0009-0002-2510-7069", "affiliations": [{"raw_affiliation_string": "School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China", "institution_ids": ["https://openalex.org/I24201400"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121133911", "display_name": "Wei He", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I24201400", "display_name": "Chengdu University of Information Technology", "ror": "https://ror.org/01yxwrh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24201400"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Wei He", "raw_affiliation_strings": ["School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China", "institution_ids": ["https://openalex.org/I24201400"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121217546", "display_name": "Qing Chang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qing Chang", "raw_affiliation_strings": ["Sain Associates, Inc., 5021 Technology Drive Northwest, Suite B2, Huntsville, AL 35805, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sain Associates, Inc., 5021 Technology Drive Northwest, Suite B2, Huntsville, AL 35805, USA", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121229142", "display_name": "Wen Luo", "orcid": "https://orcid.org/0009-0004-1409-4738", "observed_orcids": ["https://orcid.org/0009-0004-1409-4738"]}, "institutions": [{"id": "https://openalex.org/I24201400", "display_name": "Chengdu University of Information Technology", "ror": "https://ror.org/01yxwrh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24201400"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wen Luo", "raw_affiliation_strings": ["School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China"], "raw_orcid": "https://orcid.org/0009-0004-1409-4738", "affiliations": [{"raw_affiliation_string": "School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China", "institution_ids": ["https://openalex.org/I24201400"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5121189741", "display_name": "Lingli Xiao", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I24201400", "display_name": "Chengdu University of Information Technology", "ror": "https://ror.org/01yxwrh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I24201400"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lingli Xiao", "raw_affiliation_strings": ["School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China", "institution_ids": ["https://openalex.org/I24201400"]}]}], "abstract_inverted_index": {"Traditional": [0], "road": [1, 38], "traffic": [2, 39, 192], "accident": [3, 31, 40, 58, 88, 106, 138], "analysis": [4, 41, 189], "has": [5], "long": [6], "relied": [7], "on": [8, 44], "structured": [9, 57, 172], "data,": [10], "making": [11], "it": [12], "difficult": [13], "to": [14, 26, 77], "integrate": [15], "high-dimensional": [16], "heterogeneous": [17], "information": [18], "such": [19], "as": [20], "remote": [21, 53, 102], "sensing": [22, 54, 103], "imagery": [23, 55], "and": [24, 90, 109, 140, 149, 161, 187], "leading": [25], "an": [27, 145, 150], "incomplete": [28], "understanding": [29], "of": [30, 137, 147, 152, 171], "scene": [32], "environments.": [33], "This": [34], "study": [35], "proposes": [36], "a": [37, 61, 121, 182], "framework": [42], "based": [43], "Multimodal": [45], "Large": [46], "Language": [47], "Models.": [48], "The": [49], "approach": [50], "integrates": [51], "high-resolution": [52], "with": [56], "data": [59], "through": [60], "three-stage": [62], "progressive": [63], "training": [64], "pipeline.": [65], "Specifically,": [66], "we": [67], "fine-tune": [68], "three": [69], "open-source": [70], "vision\u2013language": [71], "models": [72], "using": [73], "Low-Rank": [74], "Adaptation": [75], "(LoRA)": [76], "sequentially": [78], "optimize": [79], "the": [80, 117, 125, 133, 142, 155, 169], "model\u2019s": [81], "capabilities": [82], "in": [83, 124, 175], "visual": [84], "environmental": [85], "description,": [86], "multi-task": [87], "classification,": [89], "Chain-of-Thought": [91], "(CoT)": [92], "driven": [93], "causal": [94], "reasoning.": [95], "A": [96], "multimodal": [97, 176], "dataset": [98], "was": [99], "constructed": [100], "containing": [101], "image": [104, 129], "descriptions,": [105], "classification": [107, 135], "labels,": [108], "interpretable": [110, 186], "reasoning": [111, 157, 173], "chains.": [112], "Experimental": [113], "results": [114, 167], "show": [115], "that": [116], "fine-tuned": [118], "model": [119, 143], "achieved": [120, 144], "maximum": [122], "improvement": [123], "CIDEr": [126, 162], "score": [127], "for": [128, 178, 190], "description": [130], "tasks.": [131], "In": [132, 154], "joint": [134], "task": [136], "severity": [139], "duration,": [141], "accuracy": [146], "71.61%": [148], "F1-score": [151], "0.8473.": [153], "CoT": [156], "task,": [158], "both": [159], "METEOR": [160], "scores": [163], "improved": [164], "significantly.": [165], "These": [166], "validate": [168], "effectiveness": [170], "mechanisms": [174], "fusion": [177], "transportation": [179], "applications,": [180], "providing": [181], "feasible": [183], "path": [184], "toward": [185], "intelligent": [188], "real-world": [191], "management.": [193]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9086999893188477, "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": 0.9086999893188477, "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/T10370", "display_name": "Traffic and Road Safety", "score": 0.07029999792575836, "subfield": {"id": "https://openalex.org/subfields/2213", "display_name": "Safety, Risk, Reliability and Quality"}, "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": 0.006000000052154064, "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:10.3390/ijgi15010008", "is_oa": true, "landing_page_url": "https://doi.org/10.3390/ijgi15010008", "pdf_url": null, "source": {"id": "https://openalex.org/S2764431341", "display_name": "ISPRS International Journal of Geo-Information", "issn_l": "2220-9964", "issn": ["2220-9964"], "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/P4310310987", "host_organization_name": "Multidisciplinary Digital Publishing Institute", "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "journal"}, "license": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "ISPRS International Journal of Geo-Information", "raw_type": "journal-article"}, "cited_by_count": 2, "is_retracted": false}, {"id": "https://openalex.org/W4413394193", "doi": "https://doi.org/10.1007/s10462-025-11330-7", "title": "Inclusive prompt engineering for large language models: a modular framework for ethical, structured, and adaptive AI", "publication_year": 2025, "publication_date": "2025-08-21", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5091732654", "display_name": "Mohammad Saleh Torkestani", "orcid": "https://orcid.org/0000-0001-5895-6660", "observed_orcids": ["https://orcid.org/0000-0001-5895-6660"]}, "institutions": [{"id": "https://openalex.org/I23923803", "display_name": "University of Exeter", "ror": "https://ror.org/03yghzc09", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I23923803"]}], "countries": ["GB"], "is_corresponding": true, "raw_author_name": "Mohamad Saleh Torkestani", "raw_affiliation_strings": ["Faculty of Environment, Science and Economy, University of Exeter, 1.65a Streatham Court, Rennes Drive, Exeter, EX4 4PU, UK"], "raw_orcid": "https://orcid.org/0000-0001-5895-6660", "affiliations": [{"raw_affiliation_string": "Faculty of Environment, Science and Economy, University of Exeter, 1.65a Streatham Court, Rennes Drive, Exeter, EX4 4PU, UK", "institution_ids": ["https://openalex.org/I23923803"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5022564157", "display_name": "Ali Alameer", "orcid": "https://orcid.org/0000-0002-7969-3609", "observed_orcids": ["https://orcid.org/0000-0002-7969-3609"]}, "institutions": [{"id": "https://openalex.org/I54459138", "display_name": "University of Salford", "ror": "https://ror.org/01tmqtf75", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I54459138"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Ali Alameer", "raw_affiliation_strings": ["School of Science, Engineering & Environment, University of Salford, Manchester, UK"], "raw_orcid": "https://orcid.org/0000-0002-7969-3609", "affiliations": [{"raw_affiliation_string": "School of Science, Engineering & Environment, University of Salford, Manchester, UK", "institution_ids": ["https://openalex.org/I54459138"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025871978", "display_name": "Palaiahnakote Shivakumara", "orcid": "https://orcid.org/0000-0001-9026-4613", "observed_orcids": ["https://orcid.org/0000-0001-9026-4613"]}, "institutions": [{"id": "https://openalex.org/I54459138", "display_name": "University of Salford", "ror": "https://ror.org/01tmqtf75", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I54459138"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Shivakumara Palaiahnakote", "raw_affiliation_strings": ["School of Science, Engineering & Environment, University of Salford, Manchester, UK"], "raw_orcid": "https://orcid.org/0000-0001-9026-4613", "affiliations": [{"raw_affiliation_string": "School of Science, Engineering & Environment, University of Salford, Manchester, UK", "institution_ids": ["https://openalex.org/I54459138"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5042034157", "display_name": "Taha Mansouri", "orcid": "https://orcid.org/0000-0003-1539-5546", "observed_orcids": ["https://orcid.org/0000-0003-1539-5546"]}, "institutions": [{"id": "https://openalex.org/I54459138", "display_name": "University of Salford", "ror": "https://ror.org/01tmqtf75", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I54459138"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Taha Manosuri", "raw_affiliation_strings": ["School of Science, Engineering & Environment, University of Salford, Manchester, UK"], "raw_orcid": "https://orcid.org/0000-0003-1539-5546", "affiliations": [{"raw_affiliation_string": "School of Science, Engineering & Environment, University of Salford, Manchester, UK", "institution_ids": ["https://openalex.org/I54459138"]}]}], "abstract_inverted_index": {"Abstract": [0], "Large": [1], "language": [2], "models": [3], "have": [4], "achieved": [5], "impressive": [6], "results": [7], "across": [8, 22, 90], "various": [9], "tasks": [10, 91], "but": [11], "remain": [12], "limited": [13], "in": [14, 92, 120, 127, 135, 157, 167], "their": [15], "ability": [16], "to": [17, 40, 116, 194], "adapt": [18], "ethically": [19], "and": [20, 45, 67, 73, 76, 78, 85, 99, 130, 164, 175, 181, 191], "structurally": [21], "diverse": [23], "domains": [24], "without": [25, 140], "retraining.": [26], "This": [27], "paper": [28], "presents": [29], "the": [30, 195], "Inclusive": [31], "Prompt": [32], "Engineering": [33], "Model": [34], "(IPEM),": [35], "a": [36, 109, 123, 168, 173], "modular": [37], "framework": [38, 186], "designed": [39], "enhance": [41], "LLM": [42], "performance,": [43, 153], "adaptability,": [44], "ethical": [46, 162], "alignment": [47], "through": [48], "prompt-level": [49], "strategies": [50], "alone.": [51], "IPEM": [52, 103, 145, 171], "integrates": [53], "four": [54], "components:": [55], "Memory-of-Thought": [56], "for": [57, 63, 71, 178], "multi-turn": [58], "consistency,": [59], "Enhanced": [60], "Chain-of-Thought": [61], "prompting": [62], "logical": [64, 128], "verification,": [65], "Structured": [66], "Analogical": [68], "Reasoning": [69], "modules": [70], "tabular": [72], "cross-domain": [74], "tasks,": [75], "Evaluation": [77], "Feedback": [79], "Loops": [80], "that": [81], "incorporate": [82], "uncertainty-aware": [83], "selection": [84], "bias": [86, 137], "mitigation": [87], "mechanisms.": [88], "Evaluated": [89], "arithmetic": [93], "reasoning,": [94], "healthcare": [95], "triage,": [96], "financial": [97], "forecasting,": [98], "inclusive": [100], "question": [101], "answering,": [102], "consistently": [104], "improves": [105], "model": [106, 142], "outputs": [107], "over": [108], "GPT-4": [110], "baseline.": [111], "Notable": [112], "outcomes": [113], "include": [114], "up": [115], "twenty": [117], "percentage": [118], "points": [119], "accuracy": [121], "gains,": [122], "25": [124], "percent": [125, 133], "reduction": [126, 134], "errors,": [129], "nearly": [131], "20": [132], "social": [136], "scores,": [138], "all": [139], "modifying": [141], "weights.": [143], "Moreover,": [144], "reduces": [146], "annotation": [147], "demands": [148], "by": [149], "one-third": [150], "while": [151], "preserving": [152], "demonstrating": [154], "its": [155], "utility": [156], "low-resource": [158], "environments.": [159], "By": [160], "unifying": [161], "safeguards": [163], "reasoning": [165], "mechanisms": [166], "prompt-based": [169], "system,": [170], "offers": [172], "reproducible": [174], "auditable": [176], "pathway": [177], "deploying": [179], "adaptable": [180], "fair": [182], "AI": [183], "systems.": [184], "The": [185], "contributes": [187], "both": [188], "practical": [189], "solutions": [190], "theoretical": [192], "insights": [193], "evolving": [196], "field": [197], "of": [198], "prompt": [199], "engineering.": [200]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8529999852180481, "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": 0.8529999852180481, "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": 0.048500001430511475, "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": 0.029100000858306885, "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": "doi:10.1007/s10462-025-11330-7", "is_oa": true, "landing_page_url": "https://doi.org/10.1007/s10462-025-11330-7", "pdf_url": "https://link.springer.com/content/pdf/10.1007/s10462-025-11330-7.pdf", "source": {"id": "https://openalex.org/S122814990", "display_name": "Artificial Intelligence Review", "issn_l": "0269-2821", "issn": ["0269-2821", "1573-7462"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "erih-plus", "jufo-1", "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": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Artificial Intelligence Review", "raw_type": "journal-article"}, "cited_by_count": 9, "is_retracted": false}, {"id": "https://openalex.org/W4415202904", "doi": "https://doi.org/10.48550/arxiv.2507.13238", "title": "Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation", "publication_year": 2025, "publication_date": "2025-07-17", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5009298179", "display_name": "Ashray Gupta", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gupta, Ashray", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Joseph, Rohan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Joseph, Rohan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5014435955", "display_name": "Sunny Rai", "orcid": "https://orcid.org/0000-0002-0677-3747", "observed_orcids": ["https://orcid.org/0000-0002-0677-3747"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rai, Sunny", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Analogies": [0], "test": [1, 120], "a": [2, 13, 55, 82, 126], "model's": [3], "ability": [4], "to": [5, 129], "infer": [6], "implicit": [7], "relationships": [8], "between": [9], "concepts,": [10], "making": [11], "them": [12], "key": [14], "benchmark": [15, 72], "for": [16, 28], "evaluating": [17], "reasoning": [18, 29, 132], "capabilities.": [19], "While": [20], "large": [21], "language": [22], "models": [23, 45, 108], "(LLMs)": [24], "are": [25], "widely": [26], "evaluated": [27], "in": [30, 34, 134], "English,": [31], "their": [32], "abilities": [33], "Indic": [35], "languages": [36], "remain": [37], "understudied,": [38], "limiting": [39], "our": [40], "understanding": [41], "of": [42, 85, 92, 115, 125], "whether": [43], "these": [44], "generalize": [46], "across": [47], "languages.": [48], "To": [49], "address": [50], "this": [51], "gap,": [52], "we": [53], "introduce": [54, 81], "new": [56], "Hindi": [57, 101], "Analogy": [58], "Test": [59], "Set": [60], "(HATS),": [61], "comprising": [62], "405": [63], "multiple-choice": [64], "questions": [65], "sourced": [66], "from": [67], "Indian": [68], "government": [69], "exams.": [70], "We": [71], "state-of-the-art": [73], "multilingual": [74], "LLMs": [75], "using": [76], "various": [77], "prompting": [78, 117], "strategies": [79], "and": [80], "grounded": [83], "Chain": [84], "Thought": [86], "approach": [87, 96], "that": [88, 107], "leverages": [89], "cognitive": [90], "theories": [91], "analogical": [93], "reasoning.": [94], "This": [95], "improves": [97], "model": [98], "performance": [99], "on": [100], "analogy": [102], "questions.": [103], "Our": [104, 119], "experiments": [105], "show": [106], "perform": [109], "best": [110], "with": [111], "English": [112], "prompts,": [113], "irrespective": [114], "the": [116, 123], "strategy.": [118], "set": [121], "addresses": [122], "lack": [124], "critical": [127], "resource": [128], "evaluate": [130], "LLM": [131], "capabilities": [133], "Hindi.": [135]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9369999766349792, "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": 0.9369999766349792, "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": 0.03779999911785126, "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": 0.01769999973475933, "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:2507.13238", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2507.13238", "pdf_url": "https://arxiv.org/pdf/2507.13238", "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/W4412649661", "doi": "https://doi.org/10.20944/preprints202507.1289.v2", "title": "iRAT: Replanning and Controlled Retrieval for Robust LLM Reasoning", "publication_year": 2025, "publication_date": "2025-07-22", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Zeeshan Ali", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I138006243", "display_name": "University of Arizona", "ror": "https://ror.org/03m2x1q45", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I138006243"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Zeeshan Ali", "raw_affiliation_strings": ["University of Arizona , USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Arizona , USA", "institution_ids": ["https://openalex.org/I138006243"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114439620", "display_name": "Praneeth Vadlapati", "orcid": "https://orcid.org/0009-0006-2592-2564", "observed_orcids": ["https://orcid.org/0009-0006-2592-2564"]}, "institutions": [{"id": "https://openalex.org/I138006243", "display_name": "University of Arizona", "ror": "https://ror.org/03m2x1q45", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I138006243"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "Praneeth Vadlapati", "raw_affiliation_strings": ["University of Arizona , USA"], "raw_orcid": "https://orcid.org/0009-0006-2592-2564", "affiliations": [{"raw_affiliation_string": "University of Arizona , USA", "institution_ids": ["https://openalex.org/I138006243"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Aryan Singh", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I138006243", "display_name": "University of Arizona", "ror": "https://ror.org/03m2x1q45", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I138006243"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Aryan Singh", "raw_affiliation_strings": ["University of Arizona , USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Arizona , USA", "institution_ids": ["https://openalex.org/I138006243"]}]}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4], "demonstrated": [5, 133], "significant": [6], "capabilities": [7], "in": [8, 54, 61, 72, 103, 138], "answering": [9], "questions": [10], "using": [11], "techniques": [12], "such": [13], "as": [14], "Chain": [15], "of": [16], "Thought": [17], "(CoT)": [18], "and": [19, 43, 52, 67, 76, 97, 108, 125, 141], "Retrieval-Augmented": [20, 38], "Generation": [21], "(RAG).": [22], "CoT": [23, 42], "enables": [24], "step-by-step": [25], "reasoning": [26, 55, 89], "to": [27, 45, 64, 111, 120, 128], "improve": [28], "accuracy,": [29], "while": [30, 144], "RAG": [31, 44], "supplements": [32], "LLMs": [33], "with": [34, 122], "relevant": [35, 116], "external": [36], "information.": [37], "Thoughts": [39], "(RAT)": [40], "combines": [41], "provide": [46], "a": [47, 87, 148], "more": [48], "robust": [49], "factual": [50], "foundation": [51], "coherence": [53], "chains.": [56], "However,": [57], "RAT": [58, 93, 137], "is": [59, 154, 164], "limited": [60], "its": [62], "ability": [63], "handle": [65], "uncertainty": [66, 102], "lacks": [68], "replanning,": [69], "often": [70], "resulting": [71], "unnecessary": [73], "retrievals,": [74], "inefficiencies,": [75], "globally": [77], "inconsistent": [78], "reasoning.": [79], "To": [80], "address": [81], "these": [82], "limitations,": [83], "we": [84], "introduce": [85], "iRAT,": [86], "novel": [88], "framework": [90], "that": [91, 134], "enhances": [92], "through": [94], "retrieval": [95], "control": [96], "replanning.": [98], "iRAT": [99, 135], "dynamically": [100], "evaluates": [101], "initial": [104], "responses,": [105], "employs": [106], "controlled": [107], "filtered": [109], "retrievals": [110, 146], "obtain": [112], "only": [113], "the": [114], "most": [115], "context,": [117], "revises": [118], "thoughts": [119], "align": [121], "new": [123], "content,": [124], "uses": [126], "replanning": [127, 163], "correct": [129], "previous": [130], "thoughts.": [131], "Evaluations": [132], "outperforms": [136], "HumanEval,": [139], "MBPP,": [140], "GSM8K": [142], "datasets,": [143], "reducing": [145], "by": [147], "considerable": [149], "amount.": [150], "The": [151, 158], "source": [152], "code": [153], "available": [155, 165], "at": [156, 166], "github.com/prane-eth/iRAT.": [157], "fine-tuned": [159], "model": [160], "used": [161], "for": [162], "huggingface.co/zeeshan5k/iRATReasoningChainEvaluatorv2.": [167]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9053000211715698, "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": 0.9053000211715698, "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": 0.021900000050663948, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.020800000056624413, "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:10.20944/preprints202507.1289.v2", "is_oa": true, "landing_page_url": "https://doi.org/10.20944/preprints202507.1289.v2", "pdf_url": "https://www.preprints.org/frontend/manuscript/39c678c08815ce8b36fd4323cea35f1f/download_pub", "source": {"id": "https://openalex.org/S6309402219", "display_name": "Preprints.org", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "repository"}, "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": 1, "is_retracted": false}, {"id": "https://openalex.org/W4412019468", "doi": "https://doi.org/10.2196/preprints.79039", "title": "Large Language Model\u2013Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review (Preprint)", "publication_year": 2025, "publication_date": "2025-06-14", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5073380371", "display_name": "Dongliang Li", "orcid": "https://orcid.org/0009-0001-8675-3702", "observed_orcids": ["https://orcid.org/0009-0001-8675-3702"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Dongliang Li", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0001-8675-3702", "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5053859600", "display_name": "Syaheerah Lebai Lutfi", "orcid": "https://orcid.org/0000-0001-7349-0061", "observed_orcids": ["https://orcid.org/0000-0001-7349-0061"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Syaheerah Lebai Lutfi", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0000-0001-7349-0061", "affiliations": []}], "abstract_inverted_index": {"BACKGROUND": [0], "Large": [1], "language": [2], "models": [3], "(LLMs),": [4], "such": [5, 231], "as": [6, 232], "GPT-3.5": [7], "and": [8, 23, 68, 77, 80, 84, 95, 111, 118, 147, 180, 184, 191, 195, 202, 224, 246, 251, 266, 289, 294, 313, 332, 343], "GPT-4": [9], "(OpenAI),": [10], "have": [11], "been": [12], "transforming": [13], "virtual": [14, 54, 140, 271], "patient": [15, 55, 66, 141, 272, 283], "systems": [16, 56, 142, 273], "in": [17, 275], "medical": [18, 58], "education": [19], "by": [20, 132], "providing": [21], "scalable": [22], "cost-effective": [24], "alternatives": [25], "to": [26, 51, 105, 336], "standardized": [27, 328], "patients.": [28], "However,": [29, 219], "systematic": [30, 48], "evaluations": [31], "of": [32, 126, 260, 317], "their": [33], "performance,": [34], "particularly": [35], "for": [36, 57, 92, 237], "multimorbidity": [37, 161, 282], "scenarios": [38], "involving": [39, 199], "multiple": [40, 277], "coexisting": [41], "diseases,": [42], "are": [43], "still": [44], "limited.": [45], "OBJECTIVE": [46], "This": [47], "review": [49], "aimed": [50], "evaluate": [52], "LLM-based": [53, 139, 270], "history-taking,": [59], "addressing": [60, 153], "four": [61], "research": [62, 297], "questions:": [63], "(1)": [64], "simulated": [65, 144], "types": [67, 157, 279], "disease": [69, 156, 278, 292], "scope,": [70], "(2)": [71], "performance-enhancing": [72], "techniques,": [73], "(3)": [74], "experimental": [75], "designs": [76], "evaluation": [78], "metrics,": [79, 223, 263, 329], "(4)": [81], "dataset": [82, 268], "characteristics": [83], "availability.": [85], "METHODS": [86], "Following": [87], "PRISMA": [88], "(Preferred": [89], "Reporting": [90], "Items": [91], "Systematic": [93], "Reviews": [94], "Meta-Analyses)": [96], "2020,": [97, 104], "9": [98], "databases": [99], "were": [100, 114, 121, 129], "searched": [101], "(January": [102], "1,": [103], "August": [106], "18,": [107], "2025).": [108], "Nontransformer": [109], "LLMs": [110], "non\u2013history-taking": [112], "tasks": [113], "excluded.": [115], "Multidimensional": [116], "quality": [117], "bias": [119, 245], "assessments": [120], "conducted.": [122], "RESULTS": [123], "A": [124], "total": [125], "39": [127], "studies": [128, 256], "included,": [130], "screened": [131], "one": [133], "computer": [134], "science": [135], "researcher": [136], "under": [137], "supervision.": [138], "mainly": [143], "internal": [145], "medicine": [146], "mental": [148], "health": [149], "disorders,": [150], "with": [151, 304], "many": [152], "distinct": [154], "single": [155], "but": [158, 280], "few": [159], "covering": [160], "or": [162], "rare": [163], "conditions.": [164], "Techniques": [165], "like": [166], "role-based": [167], "prompts,": [168], "few-shot": [169], "learning,": [170], "multiagent": [171], "frameworks,": [172], "knowledge": [173], "graph": [174], "(KG)": [175], "integration": [176], "(top-k": [177, 208], "accuracy": [178, 288], "16.02%),": [179], "fine-tuning": [181], "enhanced": [182], "dialogue": [183, 324], "diagnostic": [185, 340], "accuracy.": [186], "Multimodal": [187], "inputs": [188], "(eg,": [189, 307], "speech": [190], "imaging)": [192], "improved": [193], "immersion": [194], "realism.": [196], "Evaluations,": [197], "typically": [198], "10-50": [200], "students": [201], "3-10": [203], "experts,": [204], "demonstrated": [205], "strong": [206], "performance": [207], "accuracy:": [209], "0.45-0.98,": [210], "hallucination": [211], "rate:": [212], "0.31%\u20135%,": [213], "System": [214], "Usability": [215], "Scale": [216], "[SUS]": [217], "\u226580).": [218], "small": [220, 264], "samples,": [221], "inconsistent": [222, 262], "limited": [225, 267], "controls": [226], "restricted": [227], "generalizability.": [228], "Common": [229], "datasets": [230, 335], "MIMIC-III": [233], "(Medical": [234], "Information": [235], "Mart": [236], "Intensive": [238], "Care-III)": [239], "exhibited": [240], "intensive": [241], "care": [242], "unit": [243], "(ICU)": [244], "lacked": [247], "diversity,": [248], "affecting": [249], "reproducibility": [250], "external": [252], "validity.": [253], "CONCLUSIONS": [254], "Included": [255], "showed": [257], "moderate": [258], "risk": [259], "bias,": [261], "cohorts,": [265, 331], "transparency.": [269], "excel": [274], "simulating": [276], "lack": [281], "representation.": [284], "KGs": [285, 306], "improve": [286], "top-k": [287], "support": [290], "structured": [291], "representation": [293], "reasoning.": [295], "Future": [296], "should": [298], "prioritize": [299], "hybrid": [300], "KG-chain-of-thought": [301], "architectures": [302], "integrated": [303], "open-source": [305], "UMLS": [308], "[Unified": [309], "Medical": [310], "Language": [311], "System]": [312], "SNOMED-CT": [314], "[Systematized": [315], "Nomenclature": [316], "Medicine": [318], "-": [319], "Clinical": [320], "Terms]),": [321], "parameter-efficient": [322], "fine-tuning,": [323], "compression,": [325], "multimodal": [326, 334], "LLMs,": [327], "larger": [330], "open-access": [333], "further": [337], "enhance": [338], "realism,": [339], "accuracy,": [341], "fairness,": [342], "educational": [344], "utility.": [345]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9301999807357788, "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": 0.9301999807357788, "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/T11238", "display_name": "Simulation-Based Education in Healthcare", "score": 0.04039999842643738, "subfield": {"id": "https://openalex.org/subfields/2737", "display_name": "Physiology"}, "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/T10254", "display_name": "Innovations in Medical Education", "score": 0.00839999970048666, "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:10.2196/preprints.79039", "is_oa": false, "landing_page_url": "https://doi.org/10.2196/preprints.79039", "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/W7115887900", "doi": "https://doi.org/10.1093/foodst/vwaf056", "title": "The AI shift in food R&D", "publication_year": 2025, "publication_date": "2025-12-01", "type": "article", "language": "en", "authorships": [], "abstract_inverted_index": {"Transforming": [0], "product": [1, 56, 197, 235], "developmentThe": [2], "use": [3], "of": [4, 10, 52, 202], "artificial": [5], "intelligence": [6], "(AI)": [7], "as": [8], "part": [9], "the": [11, 23, 28, 33, 203, 212], "food": [12, 42, 62, 64, 181, 244], "design": [13], "and": [14, 43, 50, 70, 80, 85, 98, 113, 127, 139, 149, 158, 163, 179, 186, 190, 229], "development": [15, 198, 236], "process": [16], "can": [17, 30], "offer": [18], "transformative": [19], "benefits,": [20], "but": [21], "navigating": [22], "complexities": [24], "to": [25, 46, 173, 183], "successfully": [26], "leverage": [27], "opportunities": [29], "be": [31, 36], "daunting.Here,": [32], "focus": [34], "will": [35], "set": [37], "on": [38], "key": [39], "considerations": [40], "for": [41, 215], "ingredient": [44], "companies": [45], "ensure": [47], "effective": [48], "adoption": [49], "integration": [51], "AI": [53, 59, 155, 241], "across": [54, 94, 175], "new": [55, 196], "development.": [57], "The": [58], "moment": [60], "in": [61, 110, 167, 243], "innovationThe": [63], "industry's": [65, 204], "relationship": [66], "with": [67, 169, 195], "algorithmic": [68, 143], "tools": [69, 144], "machine": [71], "learning": [72], "spans": [73], "decades:": [74], "shelf": [75], "life": [76], "prediction": [77], "models,": [78], "demand": [79], "materials": [81], "planning": [82], "forecasting": [83], "systems,": [84], "delivery": [86], "route": [87], "optimisation": [88, 150], "have": [89, 232], "long": [90, 233], "provided": [91], "substantial": [92], "value": [93], "manufacturing,": [95], "logistics,": [96], "procurement,": [97], "sales": [99], "operations.These": [100], "established": [101, 170], "datadriven": [102], "methodologies": [103], "remain": [104], "essential": [105], "tools,": [106], "delivering": [107], "measurable": [108], "improvements": [109, 217], "operational": [111], "efficiency": [112], "cost": [114], "optimisation.However,": [115], "today's": [116], "large": [117], "language": [118, 121], "models": [119, 123, 172], "(LLMs),": [120], "reasoning": [122], "(LRMs),": [124], "agentic": [125], "workflows,": [126], "Model": [128], "Context": [129], "Protocol": [130], "(MCP)": [131], "capabilities": [132], "represent": [133], "a": [134], "qualitative": [135], "leap": [136], "that": [137, 218, 237], "complements": [138], "amplifies": [140], "traditional": [141], "approaches.Where": [142], "excel": [145], "at": [146], "pattern": [147], "recognition": [148], "within": [151], "defined": [152], "parameters,": [153], "modern": [154], "systems": [156], "integrate": [157], "synthesise": [159], "vast": [160], "organisational": [161], "knowledge": [162], "data": [164], "repositories.These": [165], "work": [166], "concert": [168], "statistical": [171], "reason": [174], "complex,": [176], "interconnected": [177], "variables": [178], "help": [180], "scientists": [182], "reformulate,": [184], "renew,": [185], "reframe": [187], "existing": [188, 224], "products": [189], "processes.This": [191], "is": [192, 238], "especially": [193], "so": [194], "(NPD).Product": [199], "innovation,": [200], "one": [201], "most": [205], "critical": [206], "yet": [207], "digitally": [208], "underserved": [209], "disciplines,": [210], "represents": [211], "greatest": [213], "opportunity": [214], "AI-driven": [216], "build": [219], "upon,": [220], "rather": [221], "than": [222], "replace": [223], "R&D": [225, 230, 245], "foundations.Food": [226], "industry": [227], "leaders": [228], "professionals": [231], "anticipated": [234], "faster,": [239], "moreThe": [240], "shift": [242]}, "primary_topic": {"id": "https://openalex.org/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.9628999829292297, "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/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.9628999829292297, "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/T14260", "display_name": "Impact of AI and Big Data on Business and Society", "score": 0.005200000014156103, "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/T11948", "display_name": "Machine Learning in Materials Science", "score": 0.0038999998942017555, "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"}}], "primary_location": {"id": "doi:10.1093/foodst/vwaf056", "is_oa": true, "landing_page_url": "https://doi.org/10.1093/foodst/vwaf056", "pdf_url": "https://academic.oup.com/fst/article-pdf/39/4/26/65945259/vwaf056.pdf", "source": {"id": "https://openalex.org/S4210218522", "display_name": "Food Science and Technology", "issn_l": "0950-9623", "issn": ["0950-9623", "1475-3324", "2689-1816"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": ["jufo-1", "norway-1"], "host_organization": "https://openalex.org/P4310320595", "host_organization_name": "Wiley", "host_organization_lineage": ["https://openalex.org/P4310320595"], "host_organization_lineage_names": ["Wiley"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Food Science and Technology", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7109019575", "doi": "https://doi.org/10.62441/nano-ntp.v21is1.5134", "title": "Prompt Engineering in Large Language Models: A Systematic Survey of Optimization Techniques and Real-World Applications", "publication_year": 2025, "publication_date": "2025-01-05", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Susmith Barigidad", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Susmith Barigidad", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Consequently,": [0], "over": [1], "the": [2, 33, 49, 80, 112, 133, 139, 154, 167, 182, 189, 226, 231], "past": [3], "decade,": [4], "prompt": [5, 54, 126, 159, 174, 194, 234], "engineering": [6, 55, 160, 195, 235], "as": [7, 58, 89, 151, 153], "a": [8, 45], "transformal": [9], "technique": [10], "has": [11], "emerged": [12], "to": [13, 156, 201], "optimally": [14], "facilitate": [15, 132], "large": [16], "language": [17, 22, 91], "models": [18, 23, 177], "(LLMs)": [19], "and": [20, 72, 95, 106, 115, 121, 131, 146, 188, 206, 216, 244], "vision": [21], "(VLMs)": [24], "for": [25, 172, 184], "their": [26], "transferable": [27], "usage": [28], "in": [29, 53, 102, 118, 143, 166, 207], "various": [30], "fields": [31], "without": [32], "requirement": [34], "of": [35, 40, 48, 65, 82, 141, 181, 191, 225], "model": [36, 134], "retraining.": [37], "The": [38, 223], "focus": [39], "this": [41, 109], "paper": [42, 110, 168], "is": [43, 228], "on": [44, 84], "thorough": [46], "analysis": [47], "optimization": [50, 204], "techniques": [51, 78, 183, 205], "available": [52], "field": [56], "such": [57, 88], "Zero": [59], "Shot,": [60], "Few": [61], "Shot": [62], "prompting,": [63], "Chain": [64], "Thought,": [66], "Auto": [67], "CoT,": [68], "Logical": [69], "CoT": [70], "(LogiCoT)": [71], "Retrieval": [73], "augmented": [74], "generation": [75], "(RAG).": [76], "These": [77], "boost": [79], "performance": [81], "LLMs": [83], "real-world": [85], "use": [86, 157], "cases": [87], "natural": [90], "understanding,": [92], "commonsense": [93], "reasoning": [94], "general": [96], "solving": [97], "sophisticated": [98], "problems": [99, 117], "across": [100, 220], "domains": [101], "healthcare,": [103], "finance,": [104], "education": [105], "legal": [107], "system.Additionally,": [108], "studies": [111], "biases,": [113], "fairnes,": [114], "hallucination": [116], "LLM": [119, 218], "outputs": [120], "thus": [122], "highlights": [123], "how": [124], "optimized": [125, 185], "strategies": [127], "can": [128], "resolve": [129], "them": [130], "generalization.": [135], "It": [136], "also": [137], "explains": [138], "importance": [140], "interpretability": [142], "AI": [144, 239], "systems": [145], "what": [147], "current": [148], "limitations": [149], "are,": [150], "well": [152], "need": [155], "transparent": [158], "approaches.Some": [161], "novel": [162], "research": [163, 198], "directions": [164], "suggested": [165], "are": [169], "meta": [170], "learning": [171], "dynamic": [173], "adaptation,": [175], "hybrid": [176], "that": [178, 229], "combine": [179], "few": [180], "task": [186], "performance,": [187], "feasibility": [190], "an": [192], "autonomous": [193], "system.": [196], "This": [197], "push": [199, 238], "forward": [200, 213], "understanding": [202], "these": [203], "doing": [208], "so,": [209], "will": [210, 236], "help": [211], "put": [212], "more": [214], "efficient": [215], "equitable": [217], "deployment": [219], "different": [221], "applications.": [222], "conlcusion": [224], "study": [227], "putting": [230], "effort": [232], "into": [233], "greatly": [237], "capabilities,": [240], "while": [241], "developing": [242], "fair": [243], "interpretable": [245], "systems.": [246]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.92330002784729, "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": 0.92330002784729, "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": 0.047600001096725464, "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": 0.018300000578165054, "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:10.62441/nano-ntp.v21is1.5134", "is_oa": true, "landing_page_url": "https://doi.org/10.62441/nano-ntp.v21is1.5134", "pdf_url": null, "source": {"id": "https://openalex.org/S104949663", "display_name": "Nanotechnology Perceptions", "issn_l": "1660-6795", "issn": ["1660-6795", "2235-2074"], "is_oa": true, "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": "Nanotechnology Perceptions", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4417115512", "doi": "https://doi.org/10.48550/arxiv.2506.06303", "title": "Reward Is Enough: LLMs Are In-Context Reinforcement Learners", "publication_year": 2025, "publication_date": "2025-05-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Song, Kefan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Song, Kefan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Moeini, Amir", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Moeini, Amir", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100396101", "display_name": "Peng Wang", "orcid": "https://orcid.org/0000-0002-9844-0615", "observed_orcids": ["https://orcid.org/0000-0002-9844-0615"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Peng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Gong, Lei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gong, Lei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5016704715", "display_name": "Rohan Chandra", "orcid": "https://orcid.org/0000-0003-4843-6375", "observed_orcids": ["https://orcid.org/0000-0003-4843-6375"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chandra, Rohan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5033834190", "display_name": "Shangtong Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Shangtong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Qi, Yanjun", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qi, Yanjun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Reinforcement": [0], "learning": [1, 66], "(RL)": [2], "is": [3, 59], "a": [4, 29, 42, 72, 86, 99, 185], "framework": [5], "for": [6, 51, 69, 189], "solving": [7], "sequential": [8], "decision-making": [9], "problems.": [10], "In": [11, 88, 121], "this": [12, 38], "work,": [13], "we": [14, 31, 40, 47, 92], "demonstrate": [15], "that,": [16], "surprisingly,": [17], "RL": [18, 34], "emerges": [19], "during": [20, 67, 131], "the": [21, 78, 89, 94, 118, 124, 170, 176], "inference": [22, 68], "time": [23], "of": [24, 56, 145], "large": [25], "language": [26], "models": [27], "(LLMs),": [28], "phenomenon": [30], "term": [32], "in-context": [33], "(ICRL).": [35], "To": [36], "reveal": [37], "capability,": [39], "introduce": [41], "simple": [43], "multi-round": [44], "prompting": [45, 58, 142, 180], "framework,": [46], "call": [48], "ICRL": [49, 57, 141, 179], "prompting,": [50], "inference-time": [52], "self-improvement.": [53], "The": [54], "goal": [55], "to": [60, 63, 136], "guide": [61], "LLMs": [62], "perform": [64], "reinforcement": [65, 137], "self-improvement": [70], "on": [71, 143], "given": [73], "task.": [74], "After": [75], "each": [76], "response,": [77], "model": [79], "receives": [80], "numerical": [81], "scalar": [82, 128], "feedback,": [83], "denoted": [84], "as": [85, 117, 163], "reward.": [87], "next": [90], "round,": [91], "prompt": [93], "LLM": [95, 125], "again": [96], "together": [97], "with": [98], "context": [100, 119], "that": [101, 113], "concatenates": [102], "all": [103], "prior": [104], "responses": [105], "and": [106, 150, 155, 165], "their": [107], "associated": [108], "rewards.": [109], "We": [110, 139], "consistently": [111], "observe": [112], "response": [114], "quality": [115], "improves": [116, 182], "grows.": [120], "other": [122], "words,": [123], "can": [126], "optimize": [127], "reward": [129, 171], "signals": [130, 172], "inference,": [132], "exhibiting": [133], "behavior": [134], "analogous": [135], "learning.": [138], "evaluate": [140], "Game": [144], "24,": [146], "creative": [147], "writing,": [148], "ScienceWorld,": [149], "Olympiad-level": [151], "math": [152], "competitions": [153], "(AIME": [154], "HMMT),": [156], "demonstrating": [157], "significant": [158], "improvements": [159], "over": [160], "baselines": [161], "such": [162], "Self-Refine": [164], "Reflexion.": [166], "Notably,": [167], "even": [168], "when": [169], "are": [173], "generated": [174], "by": [175], "same": [177], "LLM,": [178], "still": [181], "performance,": [183], "highlighting": [184], "promising": [186], "new": [187], "paradigm": [188], "test-time": [190], "scaling.": [191]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.47920000553131104, "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": 0.47920000553131104, "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": 0.16529999673366547, "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": 0.10620000213384628, "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:2506.06303", "is_oa": true, "landing_page_url": "https://arxiv.org/abs/2506.06303", "pdf_url": "https://arxiv.org/pdf/2506.06303", "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/W4411006113", "doi": "https://doi.org/10.36948/ijfmr.2025.v07i03.46661", "title": "Chain-of-Draft Prompting: A Structured Approach to Efficient AI Reasoning", "publication_year": 2025, "publication_date": "2025-06-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5117820307", "display_name": "Prasuna VG", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Prasuna VG", "raw_affiliation_strings": ["Professor, Department of CSE , Satya Institute Of Technology and Management , Vizianagaram , Andhra Pradesh , INDIA"], "raw_orcid": "https://orcid.org/0009-0007-0448-7580", "affiliations": [{"raw_affiliation_string": "Professor, Department of CSE , Satya Institute Of Technology and Management , Vizianagaram , Andhra Pradesh , INDIA", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5117820308", "display_name": "Sashibhushana Majji", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sashibhushana Majji", "raw_affiliation_strings": ["Director, Satya Institute Of Technology and Management , Vizianagaram , Andhra Pradesh , INDIA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Director, Satya Institute Of Technology and Management , Vizianagaram , Andhra Pradesh , INDIA", "institution_ids": []}]}], "abstract_inverted_index": {"Recent": [0], "advancements": [1], "in": [2, 76, 129, 141, 152], "prompt": [3], "engineering": [4], "have": [5, 18], "significantly": [6], "enhanced": [7], "the": [8, 136], "reasoning": [9, 21, 131, 144], "capabilities": [10], "of": [11, 43, 138], "AI": [12, 143, 154], "models.": [13], "Large": [14], "Language": [15], "Models": [16], "(LLMs)": [17], "transformed": [19], "complex": [20, 130], "through": [22, 86], "Chain-of-Thought": [23], "(COT)": [24], "prompting.": [25], "While": [26], "effective,": [27], "COT's": [28], "verbosity": [29], "leads": [30], "to": [31, 91, 104], "higher": [32], "computational": [33], "costs": [34], "and": [35, 96, 110, 126, 145], "latency,": [36], "posing": [37], "challenges": [38], "for": [39, 149], "efficiency-driven": [40], "applications.": [41], "Chain": [42], "Draft": [44], "(COD)": [45], "[Xu": [46], "et": [47], "al.,": [48], "2025]": [49], "offers": [50], "a": [51, 69, 147], "streamlined": [52], "alternative,": [53], "inspired": [54], "by": [55], "human": [56], "problem-solving": [57, 112], "patterns,": [58], "where": [59], "only": [60], "essential": [61], "information": [62], "is": [63], "recorded.": [64], "Chain-of-Draft": [65], "Prompting": [66], "(COD-P)": [67], "introduces": [68], "structured": [70, 139], "framework": [71], "that": [72, 117], "optimizes": [73], "iterative": [74], "refinement": [75], "AI-generated": [77], "responses.": [78], "Unlike": [79], "traditional": [80], "methods,": [81], "COD-P": [82, 118], "systematically": [83], "guides": [84], "models": [85], "incremental": [87], "drafts,": [88], "enabling": [89], "them": [90], "develop": [92], "more": [93], "coherent,": [94], "context-aware,": [95], "accurate": [97], "outputs.": [98], "This": [99], "approach": [100], "leverages": [101], "hierarchical": [102], "scaffolding": [103], "improve": [105], "logical": [106], "consistency,": [107], "minimize": [108], "hallucinations,": [109], "enhance": [111], "efficiency.": [113], "Experimental": [114], "evaluations": [115], "demonstrate": [116], "outperforms": [119], "conventional": [120], "prompting": [121, 140], "techniques,": [122], "improving": [123], "coherence": [124], "(+19.4%)": [125], "accuracy": [127], "(+13.3%)": [128], "tasks.": [132], "The": [133], "findings": [134], "underscore": [135], "importance": [137], "advancing": [142], "provide": [146], "foundation": [148], "future": [150], "improvements": [151], "interactive": [153], "methodologies.": [155]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8920999765396118, "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": 0.8920999765396118, "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": 0.05979999899864197, "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": 0.013399999588727951, "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:10.36948/ijfmr.2025.v07i03.46661", "is_oa": true, "landing_page_url": "https://doi.org/10.36948/ijfmr.2025.v07i03.46661", "pdf_url": "https://www.ijfmr.com/papers/2025/3/46661.pdf", "source": {"id": "https://openalex.org/S4210207214", "display_name": "International Journal For Multidisciplinary Research", "issn_l": "2582-2160", "issn": ["2582-2160"], "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-sa", "license_id": "https://openalex.org/licenses/cc-by-sa", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal For Multidisciplinary Research", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7106476231", "doi": null, "title": "DEPO: Dual-Efficiency Preference Optimization for LLM Agents", "publication_year": 2025, "publication_date": "2025-11-19", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Chen, Sirui", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Sirui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhao, Mengshi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Mengshi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Xu, Lei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Lei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhao, Yuying", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Yuying", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhu, Beier", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhu, Beier", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhang, Hanwang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Hanwang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhao, Shengjie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Shengjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Lu, Chaochao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lu, Chaochao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 36, 130], "large": [3], "language": [4], "models": [5], "(LLMs)": [6], "have": [7], "greatly": [8], "improved": [9], "their": [10], "reasoning": [11], "and": [12, 67, 98, 105, 117, 140], "decision-making": [13], "abilities": [14], "when": [15, 145], "deployed": [16], "as": [17], "agents.": [18], "Richer": [19], "reasoning,": [20], "however,": [21], "often": [22], "comes": [23], "at": [24, 157], "the": [25, 73, 151], "cost": [26], "of": [27, 30, 45, 75, 150], "longer": [28], "chain": [29], "thought": [31], "(CoT),": [32], "hampering": [33], "interaction": [34], "efficiency": [35, 143], "real-world": [37], "scenarios.": [38], "Nevertheless,": [39], "there": [40], "still": [41], "lacks": [42], "systematic": [43], "definition": [44], "LLM": [46], "agent": [47], "efficiency,": [48, 61, 70], "hindering": [49], "targeted": [50], "improvements.": [51], "To": [52], "this": [53, 83], "end,": [54], "we": [55, 85], "introduce": [56], "dual-efficiency,": [57], "comprising": [58], "(i)": [59], "step-level": [60], "which": [62, 71], "minimizes": [63, 72], "tokens": [64], "per": [65], "step,": [66], "(ii)": [68], "trajectory-level": [69], "number": [74], "steps": [76, 118], "to": [77, 115, 121, 126, 135], "complete": [78], "a": [79, 88, 127], "task.": [80], "Building": [81], "on": [82, 103, 147], "definition,": [84], "propose": [86], "DEPO,": [87], "dual-efficiency": [89], "preference": [90], "optimization": [91], "method": [92], "that": [93, 108], "jointly": [94], "rewards": [95], "succinct": [96], "responses": [97], "fewer": [99], "action": [100], "steps.": [101], "Experiments": [102], "WebShop": [104], "BabyAI": [106], "show": [107], "DEPO": [109, 132], "cuts": [110], "token": [111], "usage": [112], "by": [113, 119], "up": [114, 120, 125], "60.9%": [116], "26.9%,": [122], "while": [123], "achieving": [124], "29.3%": [128], "improvement": [129], "performance.": [131], "also": [133], "generalizes": [134], "three": [136], "out-of-domain": [137], "math": [138], "benchmarks": [139], "retains": [141], "its": [142], "gains": [144], "trained": [146], "only": [148], "25%": [149], "data.": [152], "Our": [153], "project": [154], "page": [155], "is": [156], "https://opencausalab.github.io/DEPO.": [158]}, "primary_topic": {"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "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"}}, "topics": [{"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "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/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.1525000035762787, "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": 0.13230000436306, "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:2511.15392", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.15392", "pdf_url": "https://arxiv.org/pdf/2511.15392", "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/W4416445771", "doi": "https://doi.org/10.36227/techrxiv.176369747.70179230/v1", "title": "Efficient Long Chain-of-Thought Elicitation through Synthetic Data Generation and Targeted Fine-Tuning", "publication_year": 2025, "publication_date": "2025-11-21", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5042342823", "display_name": "Abdulloh Abdulloh", "orcid": "https://orcid.org/0009-0003-7300-5638", "observed_orcids": ["https://orcid.org/0009-0003-7300-5638"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Abdulloh Abdulloh", "raw_affiliation_strings": ["Independent Researcher"], "raw_orcid": "https://orcid.org/0009-0003-7300-5638", "affiliations": [{"raw_affiliation_string": "Independent Researcher", "institution_ids": []}]}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 124, 270, 314], "large": [3, 107], "language": [4, 126], "model": [5, 249], "(LLM)": [6], "reasoning": [7, 18, 122, 155, 207, 213, 278], "have": [8], "demonstrated": [9], "that": [10, 74, 147, 189, 223, 292], "scaling": [11], "inference-time": [12], "compute": [13], "through": [14, 103], "long": [15, 31, 80, 87, 120, 149, 182, 284, 316], "chain-of-thought": [16], "(CoT)": [17], "can": [19], "significantly": [20], "improve": [21], "performance": [22, 230, 286], "on": [23, 36, 79, 211, 252, 257], "complex": [24], "tasks.": [25], "However,": [26], "current": [27], "approaches": [28], "for": [29, 118, 262, 283, 299], "training": [30, 89, 133], "CoT": [32, 81, 88, 121, 150, 164, 183, 285, 317], "capabilities": [33, 123], "rely": [34], "heavily": [35], "either": [37], "(1)": [38, 169], "expensive": [39], "reinforcement": [40], "learning": [41, 203, 295], "(RL)": [42], "from": [43, 53, 106, 158, 172], "base": [44], "models": [45, 56, 127, 306], "requiring": [46, 235], "massive": [47], "computational": [48, 238], "resources,": [49], "or": [50, 134], "(2)": [51, 185], "distillation": [52], "proprietary": [54, 244], "frontier": [55, 137], "like": [57], "OpenAI\u2019s": [58], "o1,": [59], "which": [60, 277], "is": [61, 297], "neither": [62], "reproducible": [63, 312], "nor": [64], "accessible": [65, 315], "to": [66, 94, 136, 178, 204, 231, 243, 260, 310], "most": [67, 281], "researchers.": [68], "Furthermore,": [69], "existing": [70, 159], "work": [71], "has": [72], "shown": [73], "while": [75, 234], "supervised": [76], "fine-tuning": [77], "(SFT)": [78], "data": [82, 90, 144, 161, 226, 254], "improves": [83], "performance,": [84], "obtaining": [85], "high-quality": [86], "remains": [91], "challenging": [92], "due": [93], "limited": [95], "availability": [96], "and": [97, 162, 175, 194, 197, 219, 240, 265, 287, 305], "the": [98], "expense": [99], "of": [100, 272], "generating": [101], "it": [102], "rejection": [104], "sampling": [105], "teacher": [108], "models.": [109, 138, 245], "In": [110], "this": [111], "work,": [112], "we": [113, 221], "investigate": [114], "computationally": [115], "efficient": [116], "methods": [117, 233], "eliciting": [119], "smaller": [125], "(\u22648B": [128], "parameters)": [129], "without": [130], "extensive": [131], "RL": [132], "access": [135, 242], "We": [139, 274], "propose": [140], "a": [141], "novel": [142], "synthetic": [143, 225, 253], "generation": [145], "framework": [146], "constructs": [148], "trajectories": [151], "by": [152], "programmatically": [153], "composing": [154], "patterns": [156, 279], "extracted": [157], "web": [160], "short": [163], "examples.": [165], "Our": [166, 246], "approach": [167, 227, 296], "combines": [168], "pattern": [170], "mining": [171], "discussion": [173], "forums": [174], "educational": [176], "content": [177], "identify": [179], "naturally": [180], "occurring": [181], "structures,": [184], "rule-based": [186], "trajectory": [187], "construction": [188], "systematically": [190], "incorporates": [191], "self-correction,": [192], "branching,": [193], "verification": [195], "steps,": [196], "(3)": [198], "targeted": [199], "SFT": [200], "with": [201], "curriculum": [202, 294], "progressively": [205], "build": [206], "capabilities.": [208], "Through": [209], "experiments": [210], "mathematical": [212], "benchmarks": [214], "including": [215], "MATH,": [216], "AIME": [217], "2024,": [218], "TheoremQA,": [220], "demonstrate": [222], "our": [224, 293], "achieves": [228, 255], "comparable": [229], "distillation-based": [232], "10\u00d7": [236], "less": [237], "resources": [239], "no": [241], "best": [247], "7B": [248], "trained": [250], "solely": [251], "52.3%": [256], "MATH-500": [258], "(compared": [259], "54.1%": [261], "QwQ-distilled": [263], "baselines)": [264], "shows": [266], "emergent": [267], "self-correction": [268], "behaviors": [269], "23%": [271], "responses.": [273], "further": [275], "analyze": [276], "are": [280], "critical": [282], "provide": [288], "ablation": [289], "studies": [290], "demonstrating": [291], "essential": [298], "stable": [300], "training.": [301, 318], "All": [302], "code,": [303], "data,": [304], "will": [307], "be": [308], "released": [309], "facilitate": [311], "research": [313]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8090999722480774, "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": 0.8090999722480774, "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": 0.04520000144839287, "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": 0.03060000017285347, "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.176369747.70179230/v1", "is_oa": true, "landing_page_url": "https://doi.org/10.36227/techrxiv.176369747.70179230/v1", "pdf_url": "https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176369747.70179230/v1", "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/W7106291136", "doi": "https://doi.org/10.48550/arxiv.2511.14773", "title": "Temporal Predictors of Outcome in Reasoning Language Models", "publication_year": 2025, "publication_date": "2025-11-03", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "David, Joey", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "David, Joey", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"The": [0], "chain-of-thought": [1], "(CoT)": [2], "paradigm": [3], "uses": [4], "the": [5, 17, 53], "elicitation": [6], "of": [7, 21, 114], "step-by-step": [8], "rationales": [9], "as": [10], "a": [11, 22, 31, 67, 78, 87, 93, 121], "proxy": [12], "for": [13, 84, 109, 126, 129], "reasoning,": [14], "gradually": [15], "refining": [16], "model's": [18], "latent": [19], "representation": [20], "solution.": [23], "However,": [24], "it": [25], "remains": [26], "unclear": [27], "just": [28], "how": [29], "early": [30], "Large": [32], "Language": [33], "Model": [34], "(LLM)": [35], "internally": [36], "commits": [37], "to": [38, 76, 117], "an": [39], "eventual": [40, 60], "outcome.": [41], "We": [42, 81], "probe": [43], "this": [44], "by": [45], "training": [46], "linear": [47], "classifiers": [48], "on": [49], "hidden": [50], "states": [51], "after": [52, 65, 119], "first": [54], "t": [55], "reasoning": [56, 110], "tokens,": [57, 69, 123], "showing": [58], "that": [59, 108], "correctness": [61], "is": [62], "highly": [63], "predictable": [64], "only": [66, 120], "few": [68, 122], "even": [70], "when": [71], "longer": [72], "outputs": [73], "are": [74, 98], "needed": [75], "reach": [77], "definite": [79], "answer.": [80], "show": [82], "that,": [83], "harder": [85], "questions,": [86], "drop": [88], "in": [89, 101], "predictive": [90], "accuracy": [91], "highlights": [92], "selection": [94], "artifact:": [95], "hard": [96], "items": [97], "disproportionately": [99], "represented": [100], "long": [102], "CoTs.": [103], "Overall,": [104], "our": [105], "results": [106], "imply": [107], "models,": [111], "internal": [112], "self-assessment": [113], "success": [115], "tends": [116], "emerge": [118], "with": [124], "implications": [125], "interpretability": [127], "and": [128], "inference-time": [130], "control.": [131]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8154000043869019, "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": 0.8154000043869019, "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/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.08229999989271164, "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": 0.03999999910593033, "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:2511.14773", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.14773", "pdf_url": "https://arxiv.org/pdf/2511.14773", "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/W7117250539", "doi": "https://doi.org/10.20944/preprints202512.1848.v1", "title": "EXa-LM: A Controlled Natural Language Bridge between Large Language Models and First-Order Logic Solvers", "publication_year": 2025, "publication_date": "2025-12-22", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5079061454", "display_name": "Francis Frydman", "orcid": "https://orcid.org/0009-0001-3610-3920", "observed_orcids": ["https://orcid.org/0009-0001-3610-3920"]}, "institutions": [], "countries": [], "is_corresponding": true, "raw_author_name": "Francis Frydman", "raw_affiliation_strings": ["Independent Researcher , France ;"], "raw_orcid": "https://orcid.org/0009-0001-3610-3920", "affiliations": [{"raw_affiliation_string": "Independent Researcher , France ;", "institution_ids": []}]}], "abstract_inverted_index": {"Large": [0], "language": [1, 24], "models": [2], "(LLMs)": [3], "have": [4], "demonstrated": [5], "logical": [6], "reasoning": [7, 144, 170], "abilities,": [8], "but": [9, 179], "their": [10], "inferences": [11, 178], "remain": [12], "non-traceable": [13], "and": [14, 29, 47, 52, 75, 96, 120, 127, 145, 195, 205], "lack": [15], "formal": [16, 53], "guarantees.": [17], "We": [18, 112], "introduce": [19], "eXa-LM,": [20], "a": [21, 35, 62, 71, 88, 104, 154, 167], "controlled": [22, 181], "natural": [23], "(CNL)": [25], "interface": [26], "between": [27, 50], "LLMs": [28, 174], "first-order": [30], "logic": [31, 99], "solvers.": [32], "Based": [33], "on": [34, 57, 115], "Controlled": [36], "Natural": [37], "Language,": [38], "our": [39], "approach": [40, 162], "aims": [41], "to": [42, 69, 123, 188], "create": [43], "an": [44], "explicit,": [45], "verifiable,": [46], "interpretable": [48], "bridge": [49], "text": [51], "logic.": [54], "It": [55], "relies": [56], "three": [58, 116], "main": [59], "components:": [60], "(1)": [61], "reformulation": [63], "prompt": [64], "that": [65, 131, 191], "constrains": [66], "the": [67, 80, 98, 164, 186], "LLM": [68], "produce": [70, 175], "set": [72], "of": [73, 92, 108, 143, 166], "facts": [74], "rules": [76], "in": [77, 172], "CNL,": [78], "(2)": [79], "semantic": [81], "analyzer": [82], "eXaSem": [83], "translating": [84], "this": [85], "CNL": [86], "into": [87], "Prolog": [89], "program": [90], "made": [91], "extended": [93], "Horn": [94], "clauses,": [95], "(3)": [97], "engine": [100], "eXaLog,": [101], "which": [102, 173], "integrates": [103], "secondorder": [105], "meta-interpreter": [106], "capable": [107], "inferring": [109], "ontological": [110], "properties.": [111], "evaluate": [113], "eXa-LM": [114, 132, 150, 184], "standard": [117], "benchmarks\u2014PrOntoQA,": [118], "ProofWriter": [119], "FOLIO\u2014comparing": [121], "it": [122], "GPT-4,": [124], "GPT-4o,": [125], "Logic-LM": [126], "LINC.": [128], "Results": [129], "show": [130], "matches": [133], "or": [134, 201], "exceeds": [135], "recent": [136], "neurosymbolic": [137], "systems": [138], "while": [139], "providing": [140], "full": [141], "traceability": [142], "intrinsic": [146], "explainability.": [147], "On": [148], "FOLIO,": [149], "achieves": [151], "92.9%": [152], "accuracy,": [153], "+1.05": [155], "point": [156], "gain": [157], "over": [158], "GPT-4o": [159], "Chain-of-Thought.": [160], "This": [161], "demonstrates": [163], "feasibility": [165], "transparent": [168], "neuro-symbolic": [169, 189], "pipeline": [171], "not": [176], "direct": [177], "formally": [180], "linguistic": [182], "representations.": [183], "opens": [185], "way": [187], "architectures": [190], "are": [192, 207], "safer,": [193], "verifiable": [194], "extensible,": [196], "ultimately": [197], "integrating": [198], "hypothetical,": [199], "abductive": [200], "inductive": [202], "reasoning.": [203], "Program": [204], "data": [206], "publicly": [208], "available": [209], "at": [210], "https://github.com/FFrydman/eXa-LM.": [211]}, "primary_topic": {"id": "https://openalex.org/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.9307000041007996, "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/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.9307000041007996, "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": 0.018200000748038292, "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": 0.012799999676644802, "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:10.20944/preprints202512.1848.v1", "is_oa": true, "landing_page_url": "https://doi.org/10.20944/preprints202512.1848.v1", "pdf_url": "https://www.preprints.org/frontend/manuscript/757d964c3a25e64499077c6c51be2a04/download_pub", "source": {"id": "https://openalex.org/S6309402219", "display_name": "Preprints.org", "issn_l": null, "issn": null, "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": null, "host_organization_name": null, "host_organization_lineage": ["https://openalex.org/P4310310987"], "host_organization_lineage_names": ["Multidisciplinary Digital Publishing Institute"], "type": "repository"}, "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/W4408519495", "doi": "https://doi.org/10.1109/tbdata.2025.3552333", "title": "NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models", "publication_year": 2025, "publication_date": "2025-03-17", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5075526311", "display_name": "Lin Mu", "orcid": "https://orcid.org/0009-0004-5547-6142", "observed_orcids": ["https://orcid.org/0009-0004-5547-6142"]}, "institutions": [{"id": "https://openalex.org/I143868143", "display_name": "Anhui University", "ror": "https://ror.org/05th6yx34", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143868143"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lin Mu", "raw_affiliation_strings": ["School of Computer Science and Technology, Anhui University, Hefei, China", "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"], "raw_orcid": "https://orcid.org/0009-0004-5547-6142", "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}, {"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China", "institution_ids": ["https://openalex.org/I143868143"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yide Cheng", "orcid": "https://orcid.org/0009-0004-4684-8469", "observed_orcids": ["https://orcid.org/0009-0004-4684-8469"]}, "institutions": [{"id": "https://openalex.org/I143868143", "display_name": "Anhui University", "ror": "https://ror.org/05th6yx34", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143868143"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yide Cheng", "raw_affiliation_strings": ["School of Computer Science and Technology, Anhui University, Hefei, China", "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"], "raw_orcid": "https://orcid.org/0009-0004-4684-8469", "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}, {"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China", "institution_ids": ["https://openalex.org/I143868143"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101618065", "display_name": "Jun Shen", "orcid": "https://orcid.org/0000-0002-1088-5549", "observed_orcids": ["https://orcid.org/0000-0002-1088-5549"]}, "institutions": [{"id": "https://openalex.org/I143868143", "display_name": "Anhui University", "ror": "https://ror.org/05th6yx34", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143868143"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jun Shen", "raw_affiliation_strings": ["School of Computer Science and Technology, Anhui University, Hefei, China", "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}, {"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China", "institution_ids": ["https://openalex.org/I143868143"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100430650", "display_name": "Yiwen Zhang", "orcid": "https://orcid.org/0000-0001-8709-1088", "observed_orcids": ["https://orcid.org/0000-0001-8709-1088"]}, "institutions": [{"id": "https://openalex.org/I143868143", "display_name": "Anhui University", "ror": "https://ror.org/05th6yx34", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143868143"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yiwen Zhang", "raw_affiliation_strings": ["School of Computer Science and Technology, Anhui University, Hefei, China", "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"], "raw_orcid": "https://orcid.org/0000-0001-8709-1088", "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}, {"raw_affiliation_string": "School of Computer Science and Technology, Anhui University, Hefei, Anhui, China", "institution_ids": ["https://openalex.org/I143868143"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5016260066", "display_name": "Hong Zhong", "orcid": "https://orcid.org/0000-0002-0392-9734", "observed_orcids": ["https://orcid.org/0000-0002-0392-9734"]}, "institutions": [{"id": "https://openalex.org/I143868143", "display_name": "Anhui University", "ror": "https://ror.org/05th6yx34", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I143868143"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hong Zhong", "raw_affiliation_strings": ["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Engineering Laboratory of IoT Security Technologies, School of Computer Science and Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China", "Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, the Anhui Engineering Laboratory of IoT Security Technologies, the School of Computer Science and Technology, and the Institute of Physical Science and Information Technology, Anhui University, Hefei, China"], "raw_orcid": "https://orcid.org/0000-0002-0392-9734", "affiliations": [{"raw_affiliation_string": "Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Engineering Laboratory of IoT Security Technologies, School of Computer Science and Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}, {"raw_affiliation_string": "Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, the Anhui Engineering Laboratory of IoT Security Technologies, the School of Computer Science and Technology, and the Institute of Physical Science and Information Technology, Anhui University, Hefei, China", "institution_ids": ["https://openalex.org/I143868143"]}]}], "abstract_inverted_index": {"Event": [0], "Extraction": [1], "involves": [2], "extracting": [3], "event-related": [4], "information": [5, 105], "such": [6, 47], "as": [7, 48, 129], "event": [8, 11, 93, 117, 176, 190], "types": [9], "and": [10, 38, 50, 73, 124], "arguments": [12], "from": [13, 67], "context,": [14], "which": [15], "has": [16], "long": [17], "been": [18], "tackled": [19], "through": [20], "well-designed": [21], "neural": [22, 109], "networks": [23], "or": [24], "fine-tuned": [25], "pre-trained": [26], "language": [27], "models.": [28], "These": [29], "approaches": [30], "require": [31], "substantial": [32], "annotated": [33], "data": [34], "for": [35, 92], "tuning": [36], "parameters": [37], "are": [39], "resource-intensive.": [40], "Recently,": [41], "Prompting": [42], "strategies": [43, 157], "with": [44], "frozen": [45], "parameters,": [46], "Chain-of-Thought": [49], "Self-Consistency,": [51], "have": [52, 168], "delivered": [53], "success": [54], "in": [55, 132, 143], "NLP": [56], "using": [57], "LLMs": [58], "by": [59], "generating": [60], "intermediate": [61, 122], "thought": [62], "steps.": [63], "However,": [64], "they": [65], "suffer": [66], "the": [68, 103, 116, 136, 138, 141, 144, 150, 160, 189], "challenge": [69], "of": [70, 75, 108, 135, 140], "error": [71], "propagation": [72], "lack": [74], "interaction": [76], "between": [77], "different": [78, 133, 164], "thoughts.": [79], "In": [80], "this": [81], "paper,": [82], "we": [83, 113, 154, 167], "proposeNeural": [84], "Network-based": [85], "Prompting(NetPrompt),": [86], "a": [87, 130], "novel": [88], "network-structured": [89], "prompting": [90], "strategy": [91], "extraction.": [94], "The": [95, 182], "core": [96], "idea": [97], "behind": [98], "NetPrompt": [99, 186], "is": [100, 127, 147], "to": [101, 158, 163, 179, 194], "imitate": [102], "excellent": [104], "integration": [106], "capabilities": [107], "network": [110], "structures.": [111], "Specifically,": [112], "first": [114], "decompose": [115], "extraction": [118, 177, 191], "problem": [119], "into": [120, 149], "diverse": [121], "subtasks,": [123], "each": [125], "subtask": [126], "represented": [128], "node": [131], "layers": [134], "network,": [137], "output": [139], "nodes": [142], "preceding": [145], "layer": [146], "fed": [148], "subsequent": [151], "layer.": [152], "Secondly,": [153], "propose": [155], "pruning": [156], "adapt": [159], "reasoning": [161], "overhead": [162], "problems.": [165], "Finally,": [166], "conducted": [169], "extensive": [170], "experiments": [171], "on": [172], "two": [173], "widely": [174], "used": [175], "benchmarks": [178], "evaluate": [180], "NetPrompt.": [181], "results": [183], "demonstrated": [184], "that": [185], "significantly": [187], "improved": [188], "performance": [192], "compared": [193], "previous": [195], "methods.": [196]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9955999851226807, "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": 0.9955999851226807, "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": 0.0017999999690800905, "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": 0.0010999999940395355, "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/tbdata.2025.3552333", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tbdata.2025.3552333", "pdf_url": null, "source": {"id": "https://openalex.org/S2491400915", "display_name": "IEEE Transactions on Big Data", "issn_l": "2332-7790", "issn": ["2332-7790", "2372-2096"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1", "norway-1"], "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 Big Data", "raw_type": "journal-article"}, "cited_by_count": 1, "is_retracted": false}, {"id": "https://openalex.org/W4416684496", "doi": "https://doi.org/10.48550/arxiv.2509.00629", "title": "Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?", "publication_year": 2025, "publication_date": "2025-08-30", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5092162513", "display_name": "Md. Tanzib Hosain", "orcid": "https://orcid.org/0009-0007-8723-7922", "observed_orcids": ["https://orcid.org/0009-0007-8723-7922", "https://orcid.org/0009-0007-8608-0265"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hosain, Md Tanzib", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5021919229", "display_name": "Md. Kishor Morol", "orcid": "https://orcid.org/0000-0002-4468-8260", "observed_orcids": ["https://orcid.org/0000-0002-4468-8260"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Morol, Md Kishor", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Among": [0], "the": [1, 21, 44, 138], "hardest": [2], "tasks": [3], "for": [4, 84], "humans": [5], "are": [6, 72], "those": [7], "found": [8], "in": [9], "competitive": [10, 85], "programming": [11, 53, 86], "where": [12], "problems": [13, 152], "require": [14], "sophisticated": [15], "algorithmic": [16, 176], "thinking,": [17], "puzzle": [18], "solving,": [19], "and": [20, 64, 68, 76, 116, 175, 184, 191], "creation": [22], "of": [23, 49, 80, 137, 150], "effective": [24], "code.": [25], "As": [26], "a": [27, 78, 100, 128, 134, 164], "domain": [28], "to": [29, 74, 123, 132], "assess": [30], "language": [31], "models": [32], "(LMs),": [33], "it": [34], "has": [35], "not": [36], "received": [37], "enough": [38], "attention,": [39], "though.": [40], "This": [41], "study": [42], "presents": [43], "ICPC": [45], "benchmark,": [46], "which": [47, 110], "consists": [48], "254": [50], "international": [51], "collegiate": [52], "contest": [54], "(ICPC)": [55], "tasks.": [56], "Each": [57], "problem": [58], "includes": [59], "official": [60], "analysis,": [61], "reference": [62], "code,": [63], "sample,": [65], "high-quality": [66], "unit,": [67], "hidden": [69], "tests.": [70], "We": [71, 187], "able": [73], "develop": [75], "evaluate": [77], "variety": [79], "LM": [81], "inference": [82, 108], "techniques": [83], "with": [87, 114, 162, 172], "these": [88], "resources.": [89], "With": [90, 105], "zero-shot": [91], "chain-of-thought": [92], "prompting,": [93], "we": [94, 126, 142], "find": [95], "that": [96, 144, 153], "o1": [97, 145], "only": [98], "achieves": [99], "19.1\\%": [101], "pass@1": [102], "solve": [103, 147], "rate.": [104], "our": [106, 181, 189], "best": [107], "technique,": [109], "combines": [111], "multi-turn": [112], "self-judge": [113], "reflection": [115], "retrieval": [117], "over": [118], "episodic": [119], "information,": [120], "raises": [121], "this": [122], "42.2\\%.": [124], "Furthermore,": [125], "conduct": [127], "new": [129], "human-in-the-loop": [130], "investigation": [131], "gain": [133], "deeper": [135], "understanding": [136], "remaining": [139], "difficulties.": [140], "Surprisingly,": [141], "discover": [143], "can": [146], "17": [148], "out": [149], "18": [151], "were": [154], "previously": [155], "unsolvable": [156], "by": [157, 180], "any": [158], "model": [159], "or": [160], "technique": [161], "just": [163], "few": [165], "specific": [166], "instructions.": [167], "A": [168], "footstep": [169], "toward": [170], "LMs": [171], "grounded,": [173], "imaginative,": [174], "thinking": [177], "is": [178], "provided": [179], "quantitative": [182], "findings": [183], "qualitative": [185], "research.": [186], "open-source": [188], "code": [190], "data": [192], "at": [193], "https://github.com/kraritt/zolve.": [194]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.420199990272522, "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": 0.420199990272522, "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/T10533", "display_name": "Teaching and Learning Programming", "score": 0.2619999945163727, "subfield": {"id": "https://openalex.org/subfields/1706", "display_name": "Computer Science Applications"}, "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/T10260", "display_name": "Software Engineering Research", "score": 0.14480000734329224, "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": "pmh:oai:arXiv.org:2509.00629", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2509.00629", "pdf_url": "https://arxiv.org/pdf/2509.00629", "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/W4414836590", "doi": "https://doi.org/10.48550/arxiv.2502.15969", "title": "Forgotten Polygons: Multimodal Large Language Models are Shape-Blind", "publication_year": 2025, "publication_date": "2025-02-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Rudman, William", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rudman, William", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019199746", "display_name": "Michal Golovanevsky", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Golovanevsky, Michal", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040676689", "display_name": "Amir Bar", "orcid": "https://orcid.org/0000-0001-8066-0495", "observed_orcids": ["https://orcid.org/0000-0001-8066-0495"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bar, Amir", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091920997", "display_name": "Vedant Palit", "orcid": "https://orcid.org/0009-0008-5202-8140", "observed_orcids": ["https://orcid.org/0009-0008-5202-8140"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Palit, Vedant", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5001226970", "display_name": "Yann LeCun", "orcid": "https://orcid.org/0000-0002-1992-2684", "observed_orcids": ["https://orcid.org/0000-0002-1992-2684"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "LeCun, Yann", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014921416", "display_name": "Carsten Eickhoff", "orcid": "https://orcid.org/0000-0001-9895-4061", "observed_orcids": ["https://orcid.org/0000-0001-9895-4061"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Eickhoff, Carsten", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5070578596", "display_name": "Ritambhara Singh", "orcid": "https://orcid.org/0000-0002-7523-160X", "observed_orcids": ["https://orcid.org/0000-0002-7523-160X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Singh, Ritambhara", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Despite": [0], "strong": [1], "performance": [2, 25], "on": [3, 26, 93, 155], "vision-language": [4], "tasks,": [5], "Multimodal": [6], "Large": [7], "Language": [8], "Models": [9], "(MLLMs)": [10], "struggle": [11], "with": [12, 15, 67], "mathematical": [13, 143], "problem-solving,": [14], "both": [16, 113], "open-source": [17], "and": [18, 48, 88, 115, 178], "state-of-the-art": [19], "models": [20, 69], "falling": [21], "short": [22], "of": [23, 41, 85, 112, 125], "human": [24], "visual-math": [27], "benchmarks.": [28], "To": [29], "systematically": [30], "examine": [31], "visual-mathematical": [32], "reasoning": [33, 57, 144, 171], "in": [34, 64, 74, 150, 172], "MLLMs,": [35], "we": [36, 133], "(1)": [37], "evaluate": [38], "their": [39], "understanding": [40], "geometric": [42], "primitives,": [43], "(2)": [44], "test": [45], "multi-step": [46, 142], "reasoning,": [47], "(3)": [49], "explore": [50], "a": [51], "potential": [52], "solution": [53], "to": [54, 108, 163], "improve": [55], "visual": [56, 130, 148, 186], "capabilities.": [58], "Our": [59, 165], "findings": [60, 166], "reveal": [61], "fundamental": [62], "shortcomings": [63], "shape": [65], "recognition,": [66], "top": [68], "achieving": [70], "under": [71], "50%": [72], "accuracy": [73, 154], "identifying": [75], "regular": [76], "polygons.": [77], "We": [78], "analyze": [79], "these": [80], "failures": [81], "through": [82], "the": [83, 110, 123], "lens": [84], "dual-process": [86], "theory": [87], "show": [89], "that": [90, 168], "MLLMs": [91, 106, 173], "rely": [92], "System": [94, 101, 169], "1": [95], "(intuitive,": [96], "memorized": [97], "associations)": [98], "rather": [99], "than": [100], "2": [102, 170], "(deliberate": [103], "reasoning).": [104], "Consequently,": [105], "fail": [107], "count": [109], "sides": [111, 126], "familiar": [114], "novel": [116], "shapes,": [117], "suggesting": [118], "they": [119], "have": [120], "neither": [121], "learned": [122], "concept": [124], "nor": [127], "effectively": [128], "process": [129], "inputs.": [131], "Finally,": [132], "propose": [134], "Visually": [135], "Cued": [136], "Chain-of-Thought": [137], "(VC-CoT)": [138], "prompting,": [139], "which": [140], "enhances": [141], "by": [145], "explicitly": [146], "referencing": [147], "annotations": [149], "diagrams,": [151], "boosting": [152], "GPT-4o's": [153], "an": [156, 175], "irregular": [157], "polygon": [158], "side-counting": [159], "task": [160], "from": [161], "7%": [162], "93%.": [164], "suggest": [167], "remains": [174], "open": [176], "problem,": [177], "visually-guided": [179], "prompting": [180], "is": [181], "essential": [182], "for": [183], "successfully": [184], "engaging": [185], "reasoning.": [187], "Code": [188], "available": [189], "at:": [190], "https://github.com/rsinghlab/Shape-Blind.": [191]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9980000257492065, "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": 0.9980000257492065, "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"}}, {"id": "https://openalex.org/T12522", "display_name": "Mathematics Education and Pedagogy", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/2604", "display_name": "Applied Mathematics"}, "field": {"id": "https://openalex.org/fields/26", "display_name": "Mathematics"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2502.15969", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.15969", "pdf_url": "https://arxiv.org/pdf/2502.15969", "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/W4417093144", "doi": "https://doi.org/10.48550/arxiv.2505.10936", "title": "Cochain: Balancing Insufficient and Excessive Collaboration in LLM Agent Workflows", "publication_year": 2025, "publication_date": "2025-05-16", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5080226615", "display_name": "Jiaxing Zhao", "orcid": "https://orcid.org/0000-0003-4548-2026", "observed_orcids": ["https://orcid.org/0000-0003-4548-2026", "https://orcid.org/0000-0002-2028-7286", "https://orcid.org/0000-0001-8365-7726"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Jiaxing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100962833", "display_name": "Hongbin Xie", "orcid": "https://orcid.org/0009-0003-3279-7018", "observed_orcids": ["https://orcid.org/0009-0003-3279-7018", "https://orcid.org/0009-0008-2057-9060"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xie, Hongbin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Lei, Yuzhen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lei, Yuzhen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5108885439", "display_name": "Xuan Song", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Song, Xuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052732099", "display_name": "Zhuoran Shi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shi, Zhuoran", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Li, Lianxin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Lianxin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5029226814", "display_name": "Shuangxue Liu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Shuangxue", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Xie, Linguo", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xie, Linguo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Zhang, Haoran", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Haoran", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4], "demonstrated": [5], "impressive": [6], "performance": [7], "in": [8, 77, 158, 177], "executing": [9], "complex": [10], "reasoning": [11, 16], "tasks.": [12, 80], "Chain-of-thought": [13], "effectively": [14, 93], "enhances": [15], "capabilities": [17], "by": [18, 32, 100, 123], "unlocking": [19], "the": [20, 34, 51, 70, 95, 140, 171], "potential": [21], "of": [22, 37, 54, 139, 147, 173], "large": [23], "models,": [24], "while": [25], "multi-agent": [26, 62, 163], "systems": [27, 63], "provide": [28], "more": [29], "comprehensive": [30], "solutions": [31], "integrating": [33], "collective": [35], "intelligence": [36], "multiple": [38, 120, 150], "agents.": [39], "However,": [40], "both": [41, 159], "approaches": [42], "face": [43], "significant": [44], "limitations.": [45], "Single-agent": [46], "with": [47, 179], "chain-of-thought,": [48], "due": [49], "to": [50, 136], "inherent": [52], "complexity": [53], "designing": [55], "cross-domain": [56], "prompts,": [57], "faces": [58], "collaboration": [59, 89, 98], "challenges.": [60], "Meanwhile,": [61], "consume": [64], "substantial": [65], "tokens": [66], "and": [67, 103, 125, 162], "inevitably": [68], "dilute": [69], "primary": [71], "problem,": [72], "which": [73], "is": [74], "particularly": [75], "problematic": [76], "business": [78, 96, 141], "workflow": [79, 97], "To": [81], "address": [82], "these": [83], "challenges,": [84], "we": [85, 110, 130], "propose": [86], "Cochain,": [87], "a": [88, 106, 127, 174], "prompting": [90], "framework": [91], "that": [92, 116, 153, 170], "solves": [94], "problem": [99], "combining": [101], "knowledge": [102, 114, 118], "prompts": [104, 128], "at": [105], "reduced": [107], "cost.": [108], "Specifically,": [109], "construct": [111], "an": [112], "integrated": [113], "graph": [115], "incorporates": [117], "from": [119], "stages.": [121], "Furthermore,": [122], "maintaining": [124], "retrieving": [126], "tree,": [129], "can": [131], "obtain": [132], "prompt": [133, 160], "information": [134], "relevant": [135], "other": [137], "stages": [138], "workflow.": [142], "We": [143], "perform": [144], "extensive": [145], "evaluations": [146], "Cochain": [148, 154, 180], "across": [149], "datasets,": [151], "demonstrating": [152], "outperforms": [155, 181], "all": [156], "baselines": [157], "engineering": [161], "LLMs.": [164], "Additionally,": [165], "expert": [166], "evaluation": [167], "results": [168], "indicate": [169], "use": [172], "small": [175], "model": [176], "combination": [178], "GPT-4.": [182]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.7240999937057495, "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": 0.7240999937057495, "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": 0.11270000040531158, "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/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.03889999911189079, "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:2505.10936", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.10936", "pdf_url": "https://arxiv.org/pdf/2505.10936", "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/W4416681990", "doi": "https://doi.org/10.48550/arxiv.2509.00125", "title": "Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning", "publication_year": 2025, "publication_date": "2025-08-29", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Li, Ang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Ang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5088634717", "display_name": "Zhihang Yuan", "orcid": "https://orcid.org/0000-0003-4259-4719", "observed_orcids": ["https://orcid.org/0000-0003-4259-4719"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yuan, Zhihang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101456454", "display_name": "Yang Zhang", "orcid": "https://orcid.org/0000-0003-3056-3069", "observed_orcids": ["https://orcid.org/0000-0003-3056-3069"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5037807288", "display_name": "Shouda Liu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Shouda", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5101431030", "display_name": "Yisen Wang", "orcid": "https://orcid.org/0000-0002-0181-2137", "observed_orcids": ["https://orcid.org/0000-0002-0181-2137"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yisen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Reinforcement": [0], "Learning": [1], "with": [2, 87], "Verifiable": [3], "Feedback": [4], "(RLVF)": [5], "has": [6], "become": [7], "a": [8, 33, 101], "key": [9], "technique": [10], "for": [11, 137, 152], "enhancing": [12], "the": [13, 46, 56, 112, 123, 141], "reasoning": [14, 47, 167], "abilities": [15], "of": [16, 74], "Large": [17], "Language": [18], "Models": [19], "(LLMs).": [20], "However,": [21], "its": [22], "reliance": [23], "on": [24, 45, 122, 164], "sparse,": [25], "outcome": [26], "based": [27, 121], "rewards,": [28], "which": [29], "only": [30, 182], "indicate": [31], "if": [32], "final": [34], "answer": [35], "is": [36, 143], "correct": [37], "or": [38], "not,": [39], "fails": [40], "to": [41, 109, 132], "provide": [42], "granular": [43], "guidance": [44], "process": [48], "itself.": [49], "This": [50], "limitation": [51], "hinders": [52], "efficient": [53], "learning,": [54], "as": [55], "model": [57, 142], "cannot": [58], "distinguish": [59], "between": [60], "high": [61, 150, 161], "quality": [62], "and": [63, 90], "inefficient": [64], "solutions,": [65], "nor": [66], "can": [67], "it": [68, 155], "learn": [69], "effectively": [70], "from": [71], "different": [72], "types": [73], "failures.": [75], "To": [76], "address": [77], "this,": [78], "we": [79], "observe": [80], "that": [81, 105, 172, 197], "an": [82, 134], "LLMs": [83], "self-certainty": [84], "often": [85], "correlates": [86], "task": [88, 118], "difficulty": [89, 119], "solution": [91], "quality.": [92], "We": [93], "introduce": [94], "Difficulty": [95], "Aware": [96], "Certainty": [97], "guided": [98], "Exploration": [99], "(DACE),": [100], "novel": [102], "RL": [103], "algorithm": [104], "leverages": [106], "this": [107, 130], "insight": [108], "dynamically": [110], "balance": [111], "exploration": [113, 147, 203], "exploitation": [114], "trade-off.": [115], "DACE": [116, 145, 173], "assesses": [117], "online": [120], "policys": [124], "success": [125], "rate.": [126], "It": [127], "then": [128], "uses": [129], "signal": [131], "modulate": [133], "intrinsic": [135], "reward:": [136], "difficult": [138], "tasks": [139], "where": [140], "struggling,": [144], "encourages": [146, 156], "by": [148, 159], "penalizing": [149], "certainty;": [151], "easier": [153], "tasks,": [154], "learning": [157], "efficiency": [158], "rewarding": [160], "certainty.": [162], "Experiments": [163], "challenging": [165], "mathematical": [166], "benchmarks": [168], "(AIME,": [169], "MATH)": [170], "show": [171], "significantly": [174], "outperforms": [175], "strong": [176], "baselines.": [177], "The": [178], "DACE-trained": [179], "models": [180], "not": [181], "achieve": [183], "higher": [184], "accuracy": [185], "but": [186], "also": [187], "demonstrate": [188], "more": [189], "robust": [190], "performance": [191], "when": [192], "scaling": [193], "test-time": [194], "compute,": [195], "validating": [196], "our": [198], "adaptive": [199], "approach": [200], "fosters": [201], "effective": [202], "without": [204], "sacrificing": [205], "precision.": [206]}, "primary_topic": {"id": "https://openalex.org/T10462", "display_name": "Reinforcement Learning in Robotics", "score": 0.8105000257492065, "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": 0.8105000257492065, "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": 0.041600000113248825, "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/T12072", "display_name": "Machine Learning and Algorithms", "score": 0.024700000882148743, "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:2509.00125", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2509.00125", "pdf_url": "https://arxiv.org/pdf/2509.00125", "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/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/W4414801144", "doi": "https://doi.org/10.48550/arxiv.2505.14999", "title": "Learning to Rank Chain-of-Thought: Using a Small Model", "publication_year": 2025, "publication_date": "2025-05-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5111089095", "display_name": "Eric Hanchen Jiang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jiang, Eric Hanchen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085445569", "display_name": "Haozheng Luo", "orcid": "https://orcid.org/0000-0001-9826-2874", "observed_orcids": ["https://orcid.org/0000-0001-9826-2874"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Haozheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Pang, Shengyuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pang, Shengyuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079741060", "display_name": "X. Li", "orcid": "https://orcid.org/0000-0003-1569-0107", "observed_orcids": ["https://orcid.org/0000-0003-1569-0107"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xiaomin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055702764", "display_name": "Zhenting Qi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qi, Zhenting", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5075978646", "display_name": "Hengli Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Hengli", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103056761", "display_name": "Cheng-Fu Yang", "orcid": "https://orcid.org/0000-0002-6916-2142", "observed_orcids": ["https://orcid.org/0000-0002-6916-2142"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Cheng-Fu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109734902", "display_name": "Zongyu Lin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lin, Zongyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044549752", "display_name": "Xinfeng Li", "orcid": "https://orcid.org/0000-0002-9686-4369", "observed_orcids": ["https://orcid.org/0000-0002-9686-4369"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xinfeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100641497", "display_name": "Hao Xu", "orcid": "https://orcid.org/0000-0002-4779-9353", "observed_orcids": ["https://orcid.org/0000-0002-4779-9353", "https://orcid.org/0009-0005-4390-4354"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Hao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5087096372", "display_name": "Kai-Wei Chang", "orcid": "https://orcid.org/0000-0001-5365-0072", "observed_orcids": ["https://orcid.org/0000-0001-5365-0072"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chang, Kai-Wei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5059211394", "display_name": "Ying Wu", "orcid": "https://orcid.org/0000-0001-6581-9816", "observed_orcids": ["https://orcid.org/0000-0001-6581-9816"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Ying Nian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "struggle": [4], "with": [5, 150], "reliable": [6], "mathematical": [7], "reasoning,": [8], "and": [9, 90, 136], "current": [10], "verification": [11], "methods": [12], "are": [13], "often": [14], "computationally": [15], "expensive.": [16], "This": [17, 94, 147], "paper": [18], "introduces": [19], "the": [20, 61, 80, 101, 116], "Energy": [21], "Outcome": [22], "Reward": [23], "Model": [24], "(EORM),": [25], "a": [26, 106, 156], "highly": [27], "efficient,": [28], "lightweight": [29], "post-hoc": [30], "verifier": [31], "designed": [32], "to": [33, 42, 48, 86, 112, 133], "address": [34], "this": [35], "challenge.": [36], "EORM": [37, 78, 130, 154], "uses": [38], "an": [39], "energy-based": [40], "framework": [41], "rank": [43], "Chain-of-Thought": [44], "(CoT)": [45], "solutions,": [46], "learning": [47], "distinguish": [49], "correct": [50], "from": [51, 105], "incorrect": [52], "reasoning": [53, 103], "using": [54], "only": [55, 67], "simple": [56], "outcome": [57], "labels,": [58], "thus": [59], "eliminating": [60], "need": [62], "for": [63, 159], "expensive": [64], "annotations.": [65], "With": [66], "55M": [68], "parameters,": [69], "over": [70], "127": [71], "times": [72], "smaller": [73], "than": [74], "typical": [75], "reward": [76], "models,": [77, 138], "boosts": [79], "accuracy": [81, 117], "of": [82, 108, 118, 144], "Llama": [83], "3": [84], "8B": [85], "90.7\\%": [87], "on": [88, 92], "GSM8k": [89], "63.7\\%": [91], "MATH.": [93], "performance": [95], "is": [96], "achieved": [97], "by": [98], "efficiently": [99], "selecting": [100], "optimal": [102], "path": [104], "pool": [107], "candidates,": [109], "allowing": [110], "it": [111, 140], "match": [113], "or": [114], "exceed": [115], "far": [119], "more": [120, 161], "resource-intensive": [121], "Best-of-N": [122], "sampling": [123], "techniques.": [124], "Crucially,": [125], "our": [126], "experiments": [127], "show": [128], "that": [129], "generalizes": [131], "effectively": [132], "out-of-distribution": [134], "problems": [135], "unseen": [137], "indicating": [139], "learns": [141], "fundamental": [142], "principles": [143], "valid": [145], "reasoning.": [146], "robustness,": [148], "combined": [149], "its": [151], "efficiency,": [152], "establishes": [153], "as": [155], "practical": [157], "tool": [158], "deploying": [160], "dependable": [162], "LLMs": [163], "in": [164], "complex,": [165], "real-world": [166], "applications.": [167]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5220000147819519, "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": 0.5220000147819519, "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": 0.11050000041723251, "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": 0.0414000004529953, "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:2505.14999", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.14999", "pdf_url": "https://arxiv.org/pdf/2505.14999", "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/W4414820780", "doi": "https://doi.org/10.48550/arxiv.2503.09674", "title": "Probabilistic Reasoning with LLMs for k-anonymity Estimation", "publication_year": 2025, "publication_date": "2025-03-12", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5034269162", "display_name": "Jonathan Zheng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zheng, Jonathan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5006053551", "display_name": "Sauvik Das", "orcid": "https://orcid.org/0000-0002-9073-8054", "observed_orcids": ["https://orcid.org/0000-0002-9073-8054"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Das, Sauvik", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039096905", "display_name": "Alan Ritter", "orcid": "https://orcid.org/0009-0001-4602-138X", "observed_orcids": ["https://orcid.org/0009-0001-4602-138X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ritter, Alan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5079390862", "display_name": "Wei Xu", "orcid": "https://orcid.org/0000-0002-6370-7930", "observed_orcids": ["https://orcid.org/0000-0002-6370-7930", "https://orcid.org/0009-0009-7584-2644"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Wei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Probabilistic": [0], "reasoning": [1, 29], "is": [2, 92, 135], "a": [3, 26, 52, 62, 74, 90, 96, 120, 136], "key": [4], "aspect": [5], "of": [6, 43, 61, 65, 78, 86, 117], "both": [7], "human": [8], "and": [9, 17, 99], "artificial": [10], "intelligence": [11], "that": [12, 56, 109, 132], "allows": [13], "for": [14, 33, 139], "handling": [15], "uncertainty": [16, 32, 134], "ambiguity": [18], "in": [19, 89], "decision-making.": [20], "In": [21], "this": [22, 110], "paper,": [23], "we": [24], "introduce": [25], "new": [27, 53], "numerical": [28], "task": [30], "under": [31], "large": [34], "language": [35], "models,": [36], "focusing": [37], "on": [38, 148], "estimating": [39], "the": [40, 58, 66, 69, 103, 114, 118], "privacy": [41], "risk": [42], "user-generated": [44], "documents": [45], "containing": [46], "privacy-sensitive": [47], "information.": [48, 71], "We": [49, 129], "propose": [50], "BRANCH,": [51], "LLM": [54, 133], "methodology": [55], "estimates": [57, 113], "k-privacy": [59], "value": [60], "text-the": [63], "size": [64], "population": [67, 91], "matching": [68], "given": [70], "BRANCH": [72], "factorizes": [73], "joint": [75], "probability": [76, 85], "distribution": [77], "personal": [79], "information": [80], "as": [81, 141], "random": [82], "variables.": [83], "The": [84], "each": [87], "factor": [88], "estimated": [93], "separately": [94], "using": [95], "Bayesian": [97], "network": [98], "combined": [100], "to": [101, 124], "compute": [102], "final": [104], "k-value.": [105], "Our": [106], "experiments": [107], "show": [108], "method": [111], "successfully": [112], "k-value": [115], "73%": [116], "time,": [119], "13%": [121], "increase": [122], "compared": [123], "o3-mini": [125], "with": [126], "chain-of-thought": [127], "reasoning.": [128], "also": [130], "find": [131], "good": [137], "indicator": [138], "accuracy,": [140], "high-variance": [142], "predictions": [143], "are": [144], "37.47%": [145], "less": [146], "accurate": [147], "average.": [149]}, "primary_topic": {"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.9965999722480774, "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": 0.9965999722480774, "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/T11045", "display_name": "Privacy, Security, and Data Protection", "score": 0.0005000000237487257, "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/T10028", "display_name": "Topic Modeling", "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": "pmh:oai:arXiv.org:2503.09674", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.09674", "pdf_url": "https://arxiv.org/pdf/2503.09674", "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/W7116929219", "doi": "https://doi.org/10.1360/sst-2025-0219", "title": "Fine-tuning of large language models for obstacle circumvention in path planning via chain-of-thought reasoning", "publication_year": 2025, "publication_date": "2025-12-23", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5121104494", "display_name": "Ruitao Wang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "RuiTao WANG", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121095633", "display_name": "Boyan Li", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "BoYan LI", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121103022", "display_name": "Xiaorong Shi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "XiaoRong SHI", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121106010", "display_name": "Yongming Wen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "YongMing WEN", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121027812", "display_name": "Rong Cheng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Rong CHENG", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121109577", "display_name": "Yue Yu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yue YU", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121062839", "display_name": "Ningning Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "NingNing ZHANG", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121082285", "display_name": "Hongyao Tang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "HongYao TANG", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5121092910", "display_name": "Yan Zheng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yan ZHENG", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5121061548", "display_name": "Jianye Hao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "JianYe HAO", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"\u98de\u884c\u5668\u5728\u590d\u6742\u73af\u5883\u4e2d\u7684\u81ea\u4e3b\u8def\u5f84\u89c4\u5212\u662f\u4fdd\u969c\u822a\u884c\u5b89\u5168\u548c\u4efb\u52a1\u6210\u529f\u7684\u5173\u952e,": [0], "\u8fd9\u8981\u6c42\u89c4\u5212\u7cfb\u7edf\u5fc5\u987b\u540c\u65f6\u6ee1\u8db3\u5b9e\u65f6\u907f\u969c\u4e0e\u6218\u7565\u5bfc\u822a\u7684\u53cc\u91cd\u8981\u6c42.": [1], "\u7136\u800c,": [2], "\u73b0\u6709\u65b9\u6cd5\u5728\u5e94\u5bf9\u52a8\u6001\u969c\u788d\u7269\u5206\u5e03\u3001\u73af\u5883\u4e0d\u786e\u5b9a\u6027\u4ee5\u53ca\u73b0\u5b9e\u7ea6\u675f\u65f6,": [3], "\u901a\u5e38\u5728\u9c81\u68d2\u6027\u3001\u6cdb\u5316\u80fd\u529b\u548c\u8ba1\u7b97\u6548\u7387\u7b49\u65b9\u9762\u5b58\u5728\u4e0d\u8db3.": [4], "\u9488\u5bf9\u8fd9\u4e00\u95ee\u9898,": [5], "\u672c\u6587\u63d0\u51fa\u4e86\u4e00\u79cd\u4e24\u9636\u6bb5\u7684\u5927\u8bed\u8a00\u6a21\u578b(LLM)\u9a71\u52a8\u7684\u98de\u884c\u5668\u8def\u5f84\u89c4\u5212\u65b9\u6cd5,": [6], "\u5145\u5206\u5229\u7528\u4e86LLM\u7684\u7a7a\u95f4\u63a8\u7406\u4e0e\u6cdb\u5316\u80fd\u529b.": [7], "\u5728\u7b2c\u4e00\u9636\u6bb5,": [8], "\u65e0\u9700\u4f9d\u8d56\u4f20\u7edf\u7684\u5efa\u56fe\u4e0e\u641c\u7d22\u6a21\u5757,": [9], "\u76f4\u63a5\u901a\u8fc7\u7ed3\u6784\u5316\u73af\u5883\u63cf\u8ff0\u548c\u4efb\u52a1\u63d0\u793a\u6a21\u677f\u5f15\u5bfc\u6a21\u578b\u751f\u6210\u53ef\u884c\u7684\u7ed5\u98de\u8def\u5f84;": [10], "\u5728\u7b2c\u4e8c\u9636\u6bb5,": [11], "\u6784\u5efa\u9ad8\u8d28\u91cf\u7684\u601d\u7ef4\u94fe\u7ed5\u98de\u63a8\u7406\u8def\u5f84\u6837\u672c,": [12], "\u5e76\u901a\u8fc7\u6709\u76d1\u7763\u5fae\u8c03\u63d0\u5347\u6a21\u578b\u5bf9\u7a7a\u95f4\u7ed3\u6784\u7684\u7406\u89e3\u548c\u8def\u5f84\u8f93\u51fa\u7684\u7a33\u5b9a\u6027,": [13], "\u5b9e\u73b0\u4ece\u901a\u7528\u6a21\u578b\u5230\u4efb\u52a1\u4e13\u7528\u6a21\u578b\u7684\u5e73\u6ed1\u8fc7\u6e21.": [14], "\u5b9e\u9a8c\u7ed3\u679c\u8868\u660e,": [15], "\u5728\u9ad8\u590d\u6742\u5ea6\u573a\u666f\u4e0b,": [16], "\u8be5\u65b9\u6cd5\u5728\u7ed5\u98de\u6210\u529f\u7387\u3001\u8def\u5f84\u5408\u7406\u6027\u4ee5\u53ca\u672a\u77e5\u73af\u5883\u9002\u5e94\u6027\u65b9\u9762\u5747\u8868\u73b0\u51fa\u663e\u8457\u63d0\u5347,": [17], "\u8fd9\u4e0d\u4ec5\u9a8c\u8bc1\u4e86LLM\u5728\u7ed3\u6784\u5316\u7a7a\u95f4\u4efb\u52a1\u4e2d\u7684\u53ef\u884c\u6027\u4e0e\u4f18\u52bf,": [18], "\u4e5f\u4e3a\u73b0\u5b9e\u7ea6\u675f\u6761\u4ef6\u4e0b\u7684\u667a\u80fd\u822a\u7a7a\u5bfc\u822a\u63d0\u4f9b\u4e86\u65b0\u7684\u89e3\u51b3\u65b9\u6848.": [19]}, "primary_topic": {"id": "https://openalex.org/T10586", "display_name": "Robotic Path Planning Algorithms", "score": 0.9911999702453613, "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/T10586", "display_name": "Robotic Path Planning Algorithms", "score": 0.9911999702453613, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.0038999998942017555, "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": 0.0007999999797903001, "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"}}], "primary_location": {"id": "doi:10.1360/sst-2025-0219", "is_oa": true, "landing_page_url": "https://doi.org/10.1360/sst-2025-0219", "pdf_url": "https://www.sciengine.com/doi/pdf/E87BED229BAD41F7AB190A629752AEC4", "source": {"id": "https://openalex.org/S4210173723", "display_name": "Scientia Sinica Technologica", "issn_l": "1674-7259", "issn": ["1674-7259", "2095-946X"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core"], "host_organization": "https://openalex.org/P4310319973", "host_organization_name": "Science China Press", "host_organization_lineage": ["https://openalex.org/P4310319973"], "host_organization_lineage_names": ["Science China Press"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "SCIENTIA SINICA Technologica", "raw_type": "journal-article"}, "cited_by_count": 0, "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/W4410219621", "doi": "https://doi.org/10.1016/j.ipm.2025.104195", "title": "Natural vs programming language in LLM knowledge graph construction", "publication_year": 2025, "publication_date": "2025-05-09", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5093291792", "display_name": "Paolo Gajo", "orcid": "https://orcid.org/0009-0009-9372-3323", "observed_orcids": ["https://orcid.org/0009-0009-9372-3323"]}, "institutions": [{"id": "https://openalex.org/I9360294", "display_name": "University of Bologna", "ror": "https://ror.org/01111rn36", "country_code": "IT", "type": "education", "lineage": ["https://openalex.org/I9360294"]}], "countries": ["IT"], "is_corresponding": false, "raw_author_name": "Paolo Gajo", "raw_affiliation_strings": ["Universit\u00e0, di Bologna, Forl\u00ec, Italy"], "raw_orcid": "https://orcid.org/0009-0009-9372-3323", "affiliations": [{"raw_affiliation_string": "Universit\u00e0, di Bologna, Forl\u00ec, Italy", "institution_ids": ["https://openalex.org/I9360294"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5067489760", "display_name": "Alberto Barr\u00f3n\u2010Cede\u00f1o", "orcid": "https://orcid.org/0000-0003-4719-3420", "observed_orcids": ["https://orcid.org/0000-0003-4719-3420"]}, "institutions": [{"id": "https://openalex.org/I9360294", "display_name": "University of Bologna", "ror": "https://ror.org/01111rn36", "country_code": "IT", "type": "education", "lineage": ["https://openalex.org/I9360294"]}], "countries": ["IT"], "is_corresponding": true, "raw_author_name": "Alberto Barr\u00f3n-Cede\u00f1o", "raw_affiliation_strings": ["Universit\u00e0, di Bologna, Forl\u00ec, Italy"], "raw_orcid": "https://orcid.org/0000-0003-4719-3420", "affiliations": [{"raw_affiliation_string": "Universit\u00e0, di Bologna, Forl\u00ec, Italy", "institution_ids": ["https://openalex.org/I9360294"]}]}], "abstract_inverted_index": {"Research": [0], "on": [1, 35, 72, 78, 89, 93, 98, 144, 168], "knowledge": [2], "graph": [3], "construction": [4], "(KGC)": [5], "has": [6, 140], "recently": [7], "shown": [8], "great": [9], "promise": [10], "also": [11], "thanks": [12], "to": [13, 57, 151], "the": [14, 22, 60, 123, 132, 173, 183, 188], "adoption": [15], "of": [16, 25, 84, 134, 176], "large": [17], "language": [18, 91, 113, 138], "models": [19, 85, 124], "(LLM)": [20], "for": [21, 102], "automatic": [23], "extraction": [24], "structured": [26], "information": [27, 103], "from": [28], "raw": [29], "text.": [30], "However,": [31], "most": [32], "works": [33], "rely": [34], "commercial,": [36], "closed-source": [37, 67], "LLMs,": [38], "hindering": [39], "reproducibility": [40], "and": [41, 50, 95, 215, 224], "accessibility.": [42], "We": [43, 80, 105, 178], "explore": [44], "KGC": [45, 208], "with": [46, 107, 125], "smaller,": [47], "open-weight": [48, 216], "LLMs": [49, 186], "investigate": [51], "whether": [52], "they": [53], "can": [54, 161, 210], "be": [55, 162, 211], "used": [56, 101], "improve": [58], "upon": [59], "results": [61, 204], "obtained": [62], "by": [63, 164, 192], "systems": [64, 209], "leveraging": [65], "bigger,": [66], "models.": [68], "Specifically,": [69], "we": [70, 120, 156], "focus": [71], "CodeKGC,": [73], "a": [74, 82, 141, 152, 159], "prompting": [75], "framework": [76], "based": [77], "GPT-3.5.": [79], "choose": [81], "variety": [83], "either": [86, 110], "pre-trained": [87], "primarily": [88], "natural": [90, 112, 137], "or": [92, 114], "code": [94], "fine-tune": [96, 106], "them": [97], "three": [99], "datasets": [100], "extraction.": [104], "prompts": [108, 126, 139], "formatted": [109], "in": [111, 181], "as": [115, 193, 195], "Python-like": [116], "scripts.": [117], "In": [118], "addition,": [119], "optionally": [121], "train": [122], "including": [127], "chain-of-thought": [128, 147], "sections.": [129], "After": [130], "fine-tuning,": [131], "choice": [133], "coding": [135], "vs": [136], "limited": [142], "impact": [143], "performance,": [145], "while": [146], "training": [148], "mostly": [149], "leads": [150], "performance": [153], "decrease.": [154], "Moreover,": [155], "show": [157, 205], "that": [158, 180, 206], "LLM": [160], "outperformed": [163], "much": [165, 189, 194], "smaller": [166, 214], "versions": [167], "this": [169], "task,": [170], "after": [171, 201], "undergoing": [172], "same": [174], "amount": [175], "training.": [177], "find": [179], "general": [182], "selected": [184], "lightweight": [185], "outperform": [187], "larger": [190], "CodeKGC": [191], "15\u201320": [196], "absolute": [197], "F": [198], "1": [199], "points": [200], "fine-tuning.": [202], "The": [203], "state-of-the-art": [207], "developed": [212], "using": [213], "models,": [217], "enhancing": [218], "research": [219], "transparency,": [220], "lowering": [221], "compute": [222], "requirements,": [223], "decreasing": [225], "third-party": [226], "API": [227], "reliance.": [228], "Code:": [229], "https://github.com/TinfFoil/natcode-llm-kgc": [230]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8622999787330627, "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": 0.8622999787330627, "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/T11273", "display_name": "Advanced Graph Neural Networks", "score": 0.0414000004529953, "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/T10215", "display_name": "Semantic Web and Ontologies", "score": 0.03920000046491623, "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.2025.104195", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.ipm.2025.104195", "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": 10, "is_retracted": false}, {"id": "https://openalex.org/W4407418969", "doi": "https://doi.org/10.1016/j.iheduc.2025.101001", "title": "Transforming online learning research: Leveraging GPT large language models for automated content analysis of cognitive presence", "publication_year": 2025, "publication_date": "2025-02-12", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5082693561", "display_name": "Daniela Castellanos-Reyes", "orcid": "https://orcid.org/0000-0002-0183-1549", "observed_orcids": ["https://orcid.org/0000-0002-0183-1549"]}, "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": "Daniela Castellanos-Reyes", "raw_affiliation_strings": ["Department of Teacher Education and Learning Sciences, North Carolina State University, Center for Technology and Innovation, 1010 Main Campus Dr, Suite 300, Raleigh, NC 27606, United States of America"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Teacher Education and Learning Sciences, North Carolina State University, Center for Technology and Innovation, 1010 Main Campus Dr, Suite 300, Raleigh, NC 27606, United States of America", "institution_ids": ["https://openalex.org/I137902535"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007499003", "display_name": "Larisa A. Olesova", "orcid": "https://orcid.org/0000-0002-1047-9081", "observed_orcids": ["https://orcid.org/0000-0002-1047-9081"]}, "institutions": [{"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": "Larisa Olesova", "raw_affiliation_strings": ["School of Teaching and Learning, College of Education, University of Florida, PO Box 117048, Gainesville, FL 32611, United States of America"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Teaching and Learning, College of Education, University of Florida, PO Box 117048, Gainesville, FL 32611, United States of America", "institution_ids": ["https://openalex.org/I33213144"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5040076091", "display_name": "Ayesha Sadaf", "orcid": "https://orcid.org/0000-0002-2751-682X", "observed_orcids": ["https://orcid.org/0000-0002-2751-682X"]}, "institutions": [{"id": "https://openalex.org/I102149020", "display_name": "University of North Carolina at Charlotte", "ror": "https://ror.org/04dawnj30", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I102149020"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ayesha Sadaf", "raw_affiliation_strings": ["Department of Educational Leadership, Cato College of Education, University of North Carolina at Charlotte, 9201 University City Blvd, Charlotte, NC 28223, United States of America"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Educational Leadership, Cato College of Education, University of North Carolina at Charlotte, 9201 University City Blvd, Charlotte, NC 28223, United States of America", "institution_ids": ["https://openalex.org/I102149020"]}]}], "abstract_inverted_index": {"The": [0, 32, 170], "last": [1], "two": [2], "decades": [3], "of": [4, 58, 97, 111, 123, 152, 185, 196, 205, 285, 297], "online": [5, 46, 200, 298, 306], "learning": [6, 47, 201, 307], "research": [7, 202, 243, 296], "vastly": [8], "flourished": [9], "by": [10], "examining": [11], "discussion": [12, 178, 299], "board": [13, 179], "text": [14, 69, 99, 180], "data": [15, 100, 212, 312], "through": [16, 71, 81], "content": [17, 50, 95, 113, 150, 283], "analysis": [18, 51, 96, 114, 151, 284], "based": [19, 101], "on": [20, 102], "constructs": [21], "like": [22], "cognitive": [23, 39], "presence": [24], "(CP)": [25], "with": [26, 160, 168, 234, 266], "the": [27, 89, 94, 107, 120, 124, 148, 182, 186, 227, 232, 281], "Practical": [28], "Inquiry": [29], "Model": [30, 127, 259, 292], "(PIM).": [31], "PIM": [33, 103], "sets": [34], "a": [35, 53, 157, 161, 219, 267, 271], "footprint": [36], "for": [37, 65, 147, 225, 237], "how": [38], "development": [40], "unfolds": [41], "in": [42, 45, 56, 88, 181, 199, 203, 280, 305], "collaborative": [43], "inquiry": [44], "experiences.": [48], "Ironically,": [49], "is": [52, 248, 303], "resource-intensive": [54], "endeavor": [55], "terms": [57, 204], "time": [59], "and": [60, 105, 109, 230, 241], "expertise,": [61], "making": [62], "researchers": [63], "look": [64], "ways": [66], "to": [67, 92, 116, 215, 273], "automate": [68, 93], "classification": [70], "ensemble": [72], "machine-learning": [73], "algorithms.": [74], "We": [75, 154, 221], "leveraged": [76], "large": [77], "language": [78], "models": [79, 87, 171], "(LLMs)": [80], "OpenAI's": [82], "Generative": [83], "Pre-Trained": [84], "Transformer": [85], "(GPT)": [86], "public": [90], "API": [91], "students'": [98, 177], "indicators": [104], "assess": [106], "reliability": [108, 167], "efficiency": [110], "automated": [112, 149, 282], "compared": [115], "human": [117], "analysis.": [118], "Using": [119], "seven": [121], "steps": [122], "Large": [125, 257, 290], "Language": [126, 258, 291], "Content": [128, 260, 293], "Analysis": [129, 294], "(LACA)": [130], "approach,": [131], "we": [132], "proposed": [133], "an": [134, 192], "AI-adapted": [135, 253], "CP": [136, 228, 254], "codebook": [137, 229, 255], "leveraging": [138], "prompt": [139, 163, 269], "engineering": [140], "techniques": [141], "(i.e.,": [142], "role,": [143], "chain-of-thought,": [144], "one-shot,": [145], "few-shot)": [146], "CP.": [153], "found": [155], "that": [156, 244], "fine-tuned": [158, 264], "model": [159, 265], "one-shot": [162, 268], "achieved": [164, 270], "moderate": [165, 272], "interrater": [166], "researchers.": [169], "were": [172], "more": [173], "reliable": [174], "when": [175], "classifying": [176], "Integration": [183], "phase": [184], "PIM.": [187], "A": [188, 251, 263], "cost": [189, 194], "comparison": [190], "showed": [191], "obvious": [193], "advantage": [195], "LACA": [197, 217, 302], "approaches": [198], "efficiency.": [206], "Nevertheless,": [207], "practitioners": [208], "still": [209], "need": [210], "considerable": [211], "literacy": [213], "skills": [214], "deploy": [216], "at": [218], "scale.": [220], "offer": [222], "theoretical": [223], "suggestions": [224], "simplifying": [226], "improving": [231], "IRR": [233], "LLM.": [235], "Implications": [236], "practice": [238], "are": [239], "discussed,": [240], "future": [242], "includes": [245], "instructional": [246], "advice": [247], "recommended.": [249], "\u2022": [250, 262, 276, 289, 301], "simplified": [252], "enhances": [256], "Analysis.": [261], "substantial": [274], "IRR.": [275], "LLMs": [277], "performed": [278], "better": [279], "CP's": [286], "integration": [287], "phase.": [288], "optimizes": [295], "data.": [300], "low-cost": [304], "research,": [308], "but": [309], "escalation": [310], "needs": [311], "literacy.": [313]}, "primary_topic": {"id": "https://openalex.org/T13910", "display_name": "Computational and Text Analysis Methods", "score": 0.48240000009536743, "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"}}, "topics": [{"id": "https://openalex.org/T13910", "display_name": "Computational and Text Analysis Methods", "score": 0.48240000009536743, "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/T10162", "display_name": "Online and Blended Learning", "score": 0.23770000040531158, "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/T11122", "display_name": "Online Learning and Analytics", "score": 0.21879999339580536, "subfield": {"id": "https://openalex.org/subfields/1706", "display_name": "Computer Science Applications"}, "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.iheduc.2025.101001", "is_oa": true, "landing_page_url": "https://doi.org/10.1016/j.iheduc.2025.101001", "pdf_url": null, "source": {"id": "https://openalex.org/S166850901", "display_name": "The Internet and Higher Education", "issn_l": "1096-7516", "issn": ["1096-7516", "1873-5525"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "erih-plus", "jufo-3", "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": "The Internet and Higher Education", "raw_type": "journal-article"}, "cited_by_count": 15, "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/W4414683742", "doi": "https://doi.org/10.48550/arxiv.2506.19140", "title": "Command-V: Pasting LLM Behaviors via Activation Profiles", "publication_year": 2025, "publication_date": "2025-06-23", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Wang, Barry", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Barry", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5026712341", "display_name": "Avi Schwarzschild", "orcid": "https://orcid.org/0000-0003-0997-4867", "observed_orcids": ["https://orcid.org/0000-0003-0997-4867"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Schwarzschild, Avi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5028501158", "display_name": "Alexander Robey", "orcid": "https://orcid.org/0009-0003-5693-2819", "observed_orcids": ["https://orcid.org/0009-0003-5693-2819"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Robey, Alexander", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076250758", "display_name": "Ali Payani", "orcid": "https://orcid.org/0000-0003-4054-2958", "observed_orcids": ["https://orcid.org/0000-0003-4054-2958"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Payani, Ali", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Fleming, Charles", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fleming, Charles", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Sun, Mingjie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Mingjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5022994077", "display_name": "Daphne Ippolito", "orcid": "https://orcid.org/0000-0001-9328-8995", "observed_orcids": ["https://orcid.org/0000-0001-9328-8995"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ippolito, Daphne", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Retrofitting": [0], "large": [1], "language": [2], "models": [3], "(LLMs)": [4], "with": [5], "new": [6], "behaviors": [7], "typically": [8], "requires": [9], "full": [10], "finetuning": [11, 110], "or": [12, 104], "distillation-costly": [13], "steps": [14], "that": [15, 33], "must": [16], "be": [17], "repeated": [18], "for": [19], "every": [20], "architecture.": [21], "In": [22, 92], "this": [23], "work,": [24], "we": [25], "introduce": [26], "Command-V,": [27], "a": [28, 41, 49, 57], "backpropagation-free": [29], "behavior": [30], "transfer": [31], "method": [32], "copies": [34], "an": [35], "existing": [36], "residual": [37], "activation": [38, 75], "adapter": [39], "from": [40], "donor": [42, 70], "model": [43], "and": [44, 67, 88, 99, 120], "pastes": [45], "its": [46], "effect": [47], "into": [48], "recipient": [50], "model.": [51], "Command-V": [52], "profiles": [53], "layer": [54], "activations": [55], "on": [56], "small": [58], "prompt": [59], "set,": [60], "derives": [61], "linear": [62], "converters": [63], "between": [64], "corresponding": [65], "layers,": [66], "applies": [68], "the": [69, 73, 84, 106], "intervention": [71], "in": [72], "recipient's": [74], "space.": [76], "This": [77], "process": [78], "does": [79], "not": [80], "require": [81], "access": [82], "to": [83], "original": [85], "training": [86], "data": [87, 121], "needs": [89], "minimal": [90], "compute.": [91, 117], "three": [93], "case": [94], "studies-safety-refusal": [95], "enhancement,": [96], "jailbreak": [97], "facilitation,": [98], "automatic": [100], "chain-of-thought": [101], "reasoning--Command-V": [102], "matches": [103], "exceeds": [105], "performance": [107], "of": [108, 114], "direct": [109], "while": [111], "using": [112], "orders": [113], "magnitude": [115], "less": [116], "Our": [118], "code": [119], "are": [122], "accessible": [123], "at": [124], "https://github.com/GithuBarry/Command-V/.": [125]}, "primary_topic": {"id": "https://openalex.org/T11689", "display_name": "Adversarial Robustness in Machine Learning", "score": 0.451200008392334, "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": 0.451200008392334, "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": 0.2728999853134155, "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": 0.20020000636577606, "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:2506.19140", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.19140", "pdf_url": "https://arxiv.org/pdf/2506.19140", "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/W4416045223", "doi": "https://doi.org/10.48550/arxiv.2502.20122", "title": "Self-Training Elicits Concise Reasoning in Large Language Models", "publication_year": 2025, "publication_date": "2025-02-27", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5119204303", "display_name": "Tergel Munkhbat", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Munkhbat, Tergel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065633783", "display_name": "Namgyu Ho", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ho, Namgyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101830280", "display_name": "Seo Hyun Kim", "orcid": "https://orcid.org/0000-0003-0218-1709", "observed_orcids": ["https://orcid.org/0000-0003-0218-1709"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kim, Seo Hyun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100530523", "display_name": "Yongjin Yang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Yongjin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082772530", "display_name": "Yujin Kim", "orcid": "https://orcid.org/0000-0002-0649-7471", "observed_orcids": ["https://orcid.org/0000-0002-0649-7471", "https://orcid.org/0009-0005-4645-9225"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kim, Yujin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5091674853", "display_name": "Se-Young Yun", "orcid": "https://orcid.org/0000-0001-6675-5113", "observed_orcids": ["https://orcid.org/0000-0001-6675-5113"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yun, Se-Young", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Chain-of-thought": [0], "(CoT)": [1], "reasoning": [2, 25, 73, 126], "has": [3], "enabled": [4], "large": [5], "language": [6], "models": [7], "(LLMs)": [8], "to": [9, 16, 51, 56], "utilize": [10], "additional": [11], "computation": [12], "through": [13], "intermediate": [14], "tokens": [15, 94], "solve": [17], "complex": [18], "tasks.": [19], "However,": [20], "we": [21, 44, 64], "posit": [22], "that": [23], "typical": [24], "traces": [26], "contain": [27], "many": [28], "redundant": [29], "tokens,": [30], "incurring": [31], "extraneous": [32], "inference": [33], "costs.": [34], "Upon": [35], "examination": [36], "of": [37, 41, 118, 131], "the": [38, 111], "output": [39, 93], "distribution": [40], "current": [42], "LLMs,": [43, 119], "find": [45], "evidence": [46], "on": [47, 95, 101, 127], "their": [48, 57], "latent": [49], "ability": [50], "reason": [52], "more": [53], "concisely,": [54], "relative": [55], "default": [58], "behavior.": [59], "To": [60], "elicit": [61], "this": [62], "capability,": [63], "propose": [65], "simple": [66], "fine-tuning": [67], "methods": [68], "which": [69], "leverage": [70], "self-generated": [71], "concise": [72, 125], "paths": [74], "obtained": [75], "by": [76], "best-of-N": [77], "sampling": [78], "and": [79, 103, 114], "few-shot": [80], "conditioning,": [81], "in": [82, 92], "task-specific": [83], "settings.": [84], "Our": [85], "combined": [86], "method": [87], "achieves": [88], "a": [89, 128], "30%": [90], "reduction": [91], "average,": [96], "across": [97], "five": [98], "model": [99], "families": [100], "GSM8K": [102], "MATH,": [104], "while": [105], "maintaining": [106], "average": [107], "accuracy.": [108], "By": [109], "exploiting": [110], "fundamental": [112], "stochasticity": [113], "in-context": [115], "learning": [116], "capabilities": [117], "our": [120], "self-training": [121], "approach": [122], "robustly": [123], "elicits": [124], "wide": [129], "range": [130], "models,": [132], "including": [133], "those": [134], "with": [135], "extensive": [136], "post-training.": [137], "Code": [138], "is": [139], "available": [140], "at": [141], "https://github.com/TergelMunkhbat/concise-reasoning": [142]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8438000082969666, "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": 0.8438000082969666, "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": 0.0681999996304512, "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": 0.016599999740719795, "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:2502.20122", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.20122", "pdf_url": "https://arxiv.org/pdf/2502.20122", "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": 1, "is_retracted": false}, {"id": "https://openalex.org/W4417184179", "doi": "https://doi.org/10.1093/arclin/acaf112", "title": "Comparing the Neuropsychology Knowledge Base of Publicly Available Large Language Models", "publication_year": 2025, "publication_date": "2025-11-18", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5009247270", "display_name": "Oscar R. Kronenberger", "orcid": "https://orcid.org/0009-0005-4923-5892", "observed_orcids": ["https://orcid.org/0009-0005-4923-5892"]}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Oscar R Kronenberger", "raw_affiliation_strings": ["Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": "https://orcid.org/0009-0005-4923-5892", "affiliations": [{"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050745766", "display_name": "Matthew Hutnyan", "orcid": "https://orcid.org/0000-0002-5429-4484", "observed_orcids": ["https://orcid.org/0000-0002-5429-4484"]}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Matthew Hutnyan", "raw_affiliation_strings": ["Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": "https://orcid.org/0000-0002-5429-4484", "affiliations": [{"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5069802552", "display_name": "Alyssa N Kaser", "orcid": "https://orcid.org/0000-0003-3224-1637", "observed_orcids": ["https://orcid.org/0000-0003-3224-1637"]}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Alyssa N Kaser", "raw_affiliation_strings": ["Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": "https://orcid.org/0000-0003-3224-1637", "affiliations": [{"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107202210", "display_name": "Leah Bullinger", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Leah Bullinger", "raw_affiliation_strings": ["Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5088039772", "display_name": "Laura H. Lacritz", "orcid": "https://orcid.org/0000-0002-0853-3704", "observed_orcids": ["https://orcid.org/0000-0002-0853-3704"]}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Laura H Lacritz", "raw_affiliation_strings": ["Department of Neurology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": "https://orcid.org/0000-0002-0853-3704", "affiliations": [{"raw_affiliation_string": "Department of Neurology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5072954257", "display_name": "C. Munro Cullum", "orcid": "https://orcid.org/0000-0001-9706-5465", "observed_orcids": ["https://orcid.org/0000-0001-9706-5465"]}, "institutions": [{"id": "https://openalex.org/I867280407", "display_name": "The University of Texas Southwestern Medical Center", "ror": "https://ror.org/05byvp690", "country_code": "US", "type": "healthcare", "lineage": ["https://openalex.org/I867280407"]}], "countries": ["US"], "is_corresponding": true, "raw_author_name": "C Munro Cullum", "raw_affiliation_strings": ["Department of Neurological Surgery, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Neurology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "Department of Neurological Surgery, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA"], "raw_orcid": "https://orcid.org/0000-0001-9706-5465", "affiliations": [{"raw_affiliation_string": "Department of Neurological Surgery, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Neurology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044,", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Neurological Surgery, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}, {"raw_affiliation_string": "Department of Psychiatry, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-9044, USA", "institution_ids": ["https://openalex.org/I867280407"]}]}], "abstract_inverted_index": {"OBJECTIVE:": [0], "Assess": [1], "the": [2, 17, 27, 36, 117, 121, 128, 164, 178, 216, 232, 249], "neuropsychology": [3, 225, 236], "knowledge": [4], "base": [5], "of": [6, 35, 39, 68, 103, 182, 199], "open-access": [7], "large": [8], "language": [9], "models": [10, 57, 89, 186, 189, 214], "(LLMs)": [11], "and": [12, 48, 99, 108, 145, 171, 202, 209, 228, 240], "inform": [13], "potential": [14], "applications": [15], "in": [16, 32, 58, 224], "field.": [18], "METHOD:": [19], "We": [20, 42, 73], "obtained": [21], "600": [22], "multiple-choice": [23], "practice": [24, 172], "questions": [25, 70, 118], "from": [26], "\"Be": [28], "Ready": [29], "for": [30, 95, 251], "ABPP": [31], "Neuropsychology\"": [33], "website": [34], "American": [37], "Academy": [38], "Clinical": [40], "Neuropsychology.": [41], "tested": [43], "OpenAI": [44, 125], "(GPT-3.5,": [45], "GPT-4,": [46], "o3-mini-high)": [47], "Google": [49], "(Gemini": [50], "1.0,": [51], "2.0": [52, 136], "Flash": [53], "Thinking": [54], "Experimental": [55], "[FTE])": [56], "two": [59], "trials": [60], "(T1:": [61], "used": [62], "20-question": [63], "blocks,": [64], "T2:": [65], "single-item": [66], "re-administration": [67], "incorrect": [69], "during": [71], "T1).": [72], "compared": [74, 97], "AI-estimated": [75], "to": [76, 197, 242], "actual": [77], "accuracy": [78, 130, 154], "using": [79], "a": [80, 92], "paired-samples": [81], "t-test,": [82], "while": [83], "binomial": [84], "logit": [85], "generalized": [86], "linear": [87], "mixed-effects": [88], "(GLMMs)": [90], "with": [91, 246], "random": [93], "intercept": [94], "item": [96], "LLMs": [98, 151, 233], "item-level": [100], "predictors": [101, 181], "(domain": [102], "practice,": [104], "word": [105], "count,": [106], "position-in-block,": [107], "higher/lower": [109], "order": [110], "question": [111], "type).": [112], "Finally,": [113], "we": [114], "thematically": [115], "analyzed": [116], "missed": [119], "by": [120, 134, 155], "top": [122], "models.": [123], "RESULTS:": [124], "o3-mini-high": [126], "demonstrated": [127], "highest": [129, 217], "(T1:87.0%,": [131], "T2:90.3%),": [132], "followed": [133], "Gemini": [135, 146], "FTE": [137], "(T1:81.7%,": [138], "T2:88.7%),": [139], "GPT-4": [140], "(T1:74.0%,": [141], "T2:85.5%),": [142], "GPT-3.5": [143], "(T1:62.5%),": [144], "1.0": [147], "(T1:52.3%).": [148], "On": [149], "average,": [150], "overestimated": [152], "their": [153], "15.8%": [156], "(87.3%": [157], "vs.": [158], "71.5%,": [159], "p": [160], "<": [161, 169, 191], ".001).": [162], "In": [163], "GLMMs,": [165], "specific": [166], "LLM": [167, 255], "(p": [168, 174, 190], ".001)": [170, 192], "domain": [173], "=": [175], ".045)": [176], "were": [177], "only": [179], "significant": [180], "accuracy.": [183], "Chain-of-thought": [184, 212], "\"reasoning\"": [185, 213], "outperformed": [187], "older": [188], "but": [193], "displayed": [194, 215, 234], "inaccuracies": [195], "pertaining": [196], "aspects": [198], "neuropsychological": [200], "testing": [201], "interpretation,": [203], "diagnostic": [204], "reasoning,": [205], "clinical": [206, 229], "decision": [207], "making,": [208], "neuroanatomy/neuroimaging.": [210], "CONCLUSIONS:": [211], "accuracy,": [218], "suggesting": [219], "they": [220], "may": [221], "have": [222], "utility": [223], "education,": [226], "research,": [227], "practice.": [230], "However,": [231], "persistent": [235], "content": [237], "area": [238], "weaknesses": [239], "tended": [241], "present": [243], "inaccurate": [244], "information": [245], "confidence,": [247], "highlighting": [248], "need": [250], "caution": [252], "when": [253], "interpreting": [254], "output.": [256]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.9907000064849854, "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": 0.9907000064849854, "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/T14414", "display_name": "Artificial Intelligence in Education", "score": 0.0019000000320374966, "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": 0.0017999999690800905, "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:10.1093/arclin/acaf112", "is_oa": false, "landing_page_url": "https://doi.org/10.1093/arclin/acaf112", "pdf_url": null, "source": {"id": "https://openalex.org/S13265631", "display_name": "Archives of Clinical Neuropsychology", "issn_l": "0887-6177", "issn": ["0887-6177", "1873-5843"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "erih-plus", "jufo-1", "ki-jl-1", "medline", "norway-1"], "host_organization": "https://openalex.org/P4310311648", "host_organization_name": "Oxford University Press", "host_organization_lineage": ["https://openalex.org/P4310311648", "https://openalex.org/P4310311647"], "host_organization_lineage_names": ["Oxford University Press", "University of Oxford"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Archives of Clinical Neuropsychology", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4407759431", "doi": "https://doi.org/10.48550/arxiv.2502.12462", "title": "Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs", "publication_year": 2025, "publication_date": "2025-02-18", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Park, Joon", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Park, Joon", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024780466", "display_name": "Kyohei Atarashi", "orcid": "https://orcid.org/0009-0007-7765-8002", "observed_orcids": ["https://orcid.org/0009-0007-7765-8002"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Atarashi, Kyohei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5088800219", "display_name": "Koh Takeuchi", "orcid": "https://orcid.org/0000-0002-3245-888X", "observed_orcids": ["https://orcid.org/0000-0002-3245-888X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Takeuchi, Koh", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5031707680", "display_name": "Hisashi Kashima", "orcid": "https://orcid.org/0000-0002-2770-0184", "observed_orcids": ["https://orcid.org/0000-0002-2770-0184"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kashima, Hisashi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"This": [0, 95], "paper": [1], "addresses": [2], "the": [3, 65, 69, 72, 164], "challenge": [4], "of": [5, 93, 129, 166], "comprehending": [6], "very": [7], "long": [8, 81], "contexts": [9], "in": [10, 40], "Large": [11], "Language": [12], "Models": [13], "(LLMs)": [14], "by": [15], "proposing": [16], "a": [17, 41, 80, 85, 195], "method": [18, 97], "that": [19, 179], "emulates": [20], "Retrieval": [21], "Augmented": [22], "Generation": [23], "(RAG)": [24], "through": [25], "specialized": [26], "prompt": [27, 161, 181], "engineering": [28], "and": [29, 71, 137, 154, 170, 192], "chain-of-thought": [30], "(CoT)": [31], "reasoning.": [32], "While": [33], "recent": [34], "LLMs": [35], "support": [36], "over": [37], "100,000": [38], "tokens": [39], "single": [42], "prompt,": [43], "simply": [44], "enlarging": [45], "context": [46], "windows": [47], "has": [48], "not": [49], "guaranteed": [50], "robust": [51], "multi-hop": [52], "reasoning": [53], "when": [54], "key": [55], "details": [56], "are": [57], "scattered": [58], "across": [59], "massive": [60], "input.": [61], "Our": [62], "approach": [63, 114, 142], "treats": [64], "model": [66], "as": [67, 149, 194], "both": [68], "retriever": [70], "reasoner:": [73], "it": [74], "first": [75], "tags": [76], "relevant": [77], "segments": [78], "within": [79], "passage,": [82], "then": [83], "employs": [84], "stepwise": [86], "CoT": [87], "workflow": [88], "to": [89, 133, 198], "integrate": [90], "these": [91], "pieces": [92], "evidence.": [94], "single-pass": [96], "thereby": [98], "reduces": [99], "reliance": [100], "on": [101, 108, 115], "an": [102], "external": [103], "retriever,": [104], "yet": [105], "maintains": [106], "focus": [107], "crucial": [109], "segments.": [110], "We": [111], "evaluate": [112], "our": [113, 141], "selected": [116], "tasks": [117], "from": [118], "BABILong,": [119], "which": [120], "interleaves": [121], "standard": [122], "bAbI": [123], "QA": [124], "problems": [125], "with": [126, 184], "large": [127], "amounts": [128], "distractor": [130], "text.": [131], "Compared": [132], "baseline": [134], "(no": [135], "retrieval)": [136], "naive": [138], "RAG": [139], "pipelines,": [140], "more": [143], "accurately": [144], "handles": [145], "multi-fact": [146], "questions": [147], "such": [148], "object": [150], "location": [151], "tracking,": [152], "counting,": [153], "indefinite": [155], "knowledge.": [156], "Furthermore,": [157], "we": [158], "analyze": [159], "how": [160], "structure,": [162], "including": [163], "order": [165], "question,": [167], "relevant-text": [168], "tags,": [169], "overall": [171], "instructions,": [172], "significantly": [173], "affects": [174], "performance.": [175], "These": [176], "findings": [177], "underscore": [178], "optimized": [180], "engineering,": [182], "combined": [183], "guided": [185], "reasoning,": [186], "can": [187], "enhance": [188], "LLMs'": [189], "long-context": [190], "comprehension": [191], "serve": [193], "lightweight": [196], "alternative": [197], "traditional": [199], "retrieval": [200], "pipelines.": [201]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.9707000255584717, "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": 0.9707000255584717, "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": 0.014800000004470348, "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/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.006300000008195639, "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": "pmh:oai:arXiv.org:2502.12462", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.12462", "pdf_url": "https://arxiv.org/pdf/2502.12462", "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/W4409129946", "doi": "https://doi.org/10.1109/tmm.2025.3557683", "title": "Multi-View User Preference Modeling for Personalized Text-to-Image Generation", "publication_year": 2025, "publication_date": "2025-01-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5000417495", "display_name": "Huaiwen Zhang", "orcid": "https://orcid.org/0000-0002-3183-9218", "observed_orcids": ["https://orcid.org/0000-0002-3183-9218"]}, "institutions": [{"id": "https://openalex.org/I2722730", "display_name": "Inner Mongolia University", "ror": "https://ror.org/0106qb496", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I2722730"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Huaiwen Zhang", "raw_affiliation_strings": ["College of Computer Science, Inner Mongolia University, Hohhot, China", "College of Computer Science, Inner Mongolia University, China"], "raw_orcid": "https://orcid.org/0000-0002-3183-9218", "affiliations": [{"raw_affiliation_string": "College of Computer Science, Inner Mongolia University, Hohhot, China", "institution_ids": ["https://openalex.org/I2722730"]}, {"raw_affiliation_string": "College of Computer Science, Inner Mongolia University, China", "institution_ids": ["https://openalex.org/I2722730"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Tianci Wu", "orcid": "https://orcid.org/0009-0009-0347-2517", "observed_orcids": ["https://orcid.org/0009-0009-0347-2517"]}, "institutions": [{"id": "https://openalex.org/I2722730", "display_name": "Inner Mongolia University", "ror": "https://ror.org/0106qb496", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I2722730"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tianci Wu", "raw_affiliation_strings": ["College of Computer Science, Inner Mongolia University, Hohhot, China", "College of Computer Science, Inner Mongolia University, China"], "raw_orcid": "https://orcid.org/0009-0009-0347-2517", "affiliations": [{"raw_affiliation_string": "College of Computer Science, Inner Mongolia University, Hohhot, China", "institution_ids": ["https://openalex.org/I2722730"]}, {"raw_affiliation_string": "College of Computer Science, Inner Mongolia University, China", "institution_ids": ["https://openalex.org/I2722730"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5039731055", "display_name": "Yinwei Wei", "orcid": "https://orcid.org/0000-0003-1791-3159", "observed_orcids": ["https://orcid.org/0000-0003-1791-3159"]}, "institutions": [{"id": "https://openalex.org/I154099455", "display_name": "Shandong University", "ror": "https://ror.org/0207yh398", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I154099455"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yinwei Wei", "raw_affiliation_strings": ["School of Software, Shandong University, Jinan, China"], "raw_orcid": "https://orcid.org/0000-0003-1791-3159", "affiliations": [{"raw_affiliation_string": "School of Software, Shandong University, Jinan, China", "institution_ids": ["https://openalex.org/I154099455"]}]}], "abstract_inverted_index": {"Personalized": [0], "text-to-image": [1, 80, 199], "generation": [2, 61, 81, 104, 171, 200], "aims": [3], "to": [4, 8, 26, 36, 46, 117, 147, 165, 195], "synthesize": [5, 37], "images": [6, 193], "tailored": [7], "individual": [9], "user": [10, 28, 53, 108, 146, 159, 167], "preferences.": [11], "Existing": [12], "methods": [13], "primarily": [14], "generate": [15], "customized": [16], "content": [17], "using": [18], "a": [19, 66, 76, 113, 131, 141, 174], "few": [20], "reference": [21], "images,": [22], "which": [23, 90], "often": [24], "struggle": [25], "mine": [27], "preferences": [29, 54, 95, 151, 168], "from": [30, 96], "historical": [31, 97, 155], "records,": [32], "and": [33, 93, 99, 121], "thus": [34], "fail": [35], "truly": [38], "personalized": [39, 79, 198], "content.": [40], "In": [41, 71], "addition,": [42], "it": [43], "is": [44, 163], "difficult": [45], "directly": [47], "incorporate": [48], "the": [49, 56, 60, 85, 103, 128, 170, 183, 188, 191, 196], "extracted": [50], "feature": [51, 57], "of": [52, 59, 130, 176, 190], "into": [55, 102, 124, 169], "space": [58], "model,": [62, 87], "since": [63], "there": [64], "exists": [65], "considerable": [67], "gap": [68], "between": [69], "them.": [70], "this": [72], "paper,": [73], "we": [74, 111, 139], "propose": [75], "novel": [77], "multi-view": [78], "method": [82, 185], "based": [83], "on": [84], "diffusion": [86], "named": [88], "MVP-Diffusion,": [89], "learns": [91], "instance-": [92], "user-level": [94, 136], "records": [98], "integrates": [100], "them": [101, 123], "model.": [105, 134], "For": [106, 135], "instance-level": [107], "preference": [109, 119, 137, 160], "modeling,": [110, 138], "employ": [112], "chain-of-thought": [114], "prompting": [115], "strategy": [116], "deduce": [118], "keywords": [120], "integrate": [122], "input": [125], "prompts": [126], "with": [127], "aid": [129], "large": [132], "language": [133], "construct": [140], "learnable": [142, 177], "embedding": [143], "for": [144], "each": [145], "capture": [148], "more": [149], "comprehensive": [150], "by": [152], "analyzing": [153], "their": [154], "records.": [156], "An": [157], "adaptive": [158], "fusion": [161], "module": [162], "proposed": [164, 184], "inject": [166], "model": [172], "via": [173], "set": [175], "parameters.": [178], "Experimental": [179], "results": [180], "demonstrate": [181], "that": [182], "significantly": [186], "enhances": [187], "personalization": [189], "generated": [192], "compared": [194], "other": [197], "methods.": [201]}, "primary_topic": {"id": "https://openalex.org/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "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/T10775", "display_name": "Generative Adversarial Networks and Image Synthesis", "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/T11714", "display_name": "Multimodal Machine Learning 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"}}, {"id": "https://openalex.org/T10203", "display_name": "Recommender Systems and Techniques", "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:10.1109/tmm.2025.3557683", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tmm.2025.3557683", "pdf_url": null, "source": {"id": "https://openalex.org/S137030581", "display_name": "IEEE Transactions on Multimedia", "issn_l": "1520-9210", "issn": ["1520-9210", "1941-0077"], "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 Transactions on Multimedia", "raw_type": "journal-article"}, "cited_by_count": 6, "is_retracted": false}, {"id": "https://openalex.org/W4417227408", "doi": "https://doi.org/10.48550/arxiv.2504.00532", "title": "SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking", "publication_year": 2025, "publication_date": "2025-04-01", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5087807199", "display_name": "Hongru Ma", "orcid": "https://orcid.org/0000-0003-1752-1622", "observed_orcids": ["https://orcid.org/0000-0003-1752-1622"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ma, Hongru", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100964904", "display_name": "Yanjie Liang", "orcid": "https://orcid.org/0009-0005-9206-0215", "observed_orcids": ["https://orcid.org/0009-0005-9206-0215"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liang, Yanjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101938449", "display_name": "Jiasheng Si", "orcid": "https://orcid.org/0000-0002-6870-5678", "observed_orcids": ["https://orcid.org/0000-0002-6870-5678"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Si, Jiasheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100664343", "display_name": "Weiyu Zhang", "orcid": "https://orcid.org/0000-0001-5244-8235", "observed_orcids": ["https://orcid.org/0000-0001-5244-8235"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Weiyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5022769003", "display_name": "Hongjiao Guan", "orcid": "https://orcid.org/0000-0002-4372-7416", "observed_orcids": ["https://orcid.org/0000-0002-4372-7416"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Guan, Hongjiao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5035746511", "display_name": "Chaoqun Zheng", "orcid": "https://orcid.org/0000-0002-6799-5212", "observed_orcids": ["https://orcid.org/0000-0002-6799-5212"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zheng, Chaoqun", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101419704", "display_name": "Bing Xu", "orcid": "https://orcid.org/0000-0003-1236-893X", "observed_orcids": ["https://orcid.org/0000-0003-1236-893X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Bing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5076564877", "display_name": "Wenpeng L\u00fc", "orcid": "https://orcid.org/0000-0002-1840-3540", "observed_orcids": ["https://orcid.org/0000-0002-1840-3540"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lu, Wenpeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2], "(LLMs)": [3], "have": [4], "revolutionized": [5], "code": [6, 32, 82, 104, 127, 160], "generation,": [7], "significantly": [8], "enhancing": [9], "developer": [10], "productivity.": [11], "However,": [12], "for": [13], "a": [14, 61, 75, 84, 89, 110], "vast": [15], "number": [16], "of": [17, 54], "users": [18, 44], "with": [19], "minimal": [20], "coding": [21, 41], "knowledge,": [22], "LLMs": [23, 98], "provide": [24], "little": [25], "support,": [26], "as": [27], "they": [28, 147], "primarily": [29], "generate": [30], "isolated": [31], "snippets": [33], "rather": [34], "than": [35, 130, 134, 141], "complete,": [36], "large-scale": [37, 159], "project": [38, 81, 114], "code.": [39], "Without": [40], "expertise,": [42], "these": [43], "struggle": [45], "to": [46, 59, 96, 156], "interpret,": [47], "modify,": [48], "and": [49, 94, 102, 112, 136, 153], "iteratively": [50], "refine": [51], "the": [52], "outputs": [53], "LLMs,": [55], "making": [56], "it": [57], "impossible": [58], "assemble": [60], "complete": [62, 79, 111], "project.": [63], "To": [64], "address": [65], "this": [66], "issue,": [67], "we": [68], "propose": [69], "Self-Rectified": [70], "Large-Scale": [71], "Code": [72], "Generator": [73], "(SRLCG),": [74], "framework": [76], "that": [77, 124], "generates": [78, 126], "multi-file": [80], "from": [83], "single": [85], "prompt.": [86], "SRLCG": [87, 125], "employs": [88], "novel": [90], "multidimensional": [91], "chain-of-thought": [92], "(CoT)": [93], "self-rectification": [95], "guide": [97], "in": [99, 158], "generating": [100], "correct": [101], "robust": [103], "files,": [105], "then": [106], "integrates": [107], "them": [108], "into": [109], "coherent": [113], "using": [115], "our": [116], "proposed": [117], "dynamic": [118], "backtracking": [119], "algorithm.": [120], "Experimental": [121], "results": [122], "show": [123], "15x": [128], "longer": [129, 133, 140], "DeepSeek-V3,": [131], "16x": [132], "GPT-4,": [135], "at": [137], "least": [138], "10x": [139], "other": [142], "leading": [143], "CoT-based": [144], "baselines.": [145], "Furthermore,": [146], "confirm": [148], "its": [149], "improved": [150], "correctness,": [151], "robustness,": [152], "performance": [154], "compared": [155], "baselines": [157], "generation.": [161]}, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.9980000257492065, "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": 0.9980000257492065, "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": 0.000699999975040555, "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/T10533", "display_name": "Teaching and Learning Programming", "score": 0.00019999999494757503, "subfield": {"id": "https://openalex.org/subfields/1706", "display_name": "Computer Science Applications"}, "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:2504.00532", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.00532", "pdf_url": "https://arxiv.org/pdf/2504.00532", "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/W7128196244", "doi": "https://doi.org/10.37965/jait.2025.0811", "title": "Three Large Language Models for Solidity Smart Contract Vulnerability Detection", "publication_year": 2025, "publication_date": "2025-08-14", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5117235971", "display_name": "Amjad Almaghthawi", "orcid": "https://orcid.org/0009-0003-4571-3311", "observed_orcids": ["https://orcid.org/0009-0003-4571-3311"]}, "institutions": [{"id": "https://openalex.org/I23075662", "display_name": "Taibah University", "ror": "https://ror.org/01xv1nn60", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I23075662"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Amjad Almaghthawi", "raw_affiliation_strings": ["Faculty of Computer Science Department, College of Computer Science and Engineering, Taibah University"], "raw_orcid": "https://orcid.org/0009-0003-4571-3311", "affiliations": [{"raw_affiliation_string": "Faculty of Computer Science Department, College of Computer Science and Engineering, Taibah University", "institution_ids": ["https://openalex.org/I23075662"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010105706", "display_name": "Wael M. S. Yafooz", "orcid": "https://orcid.org/0000-0002-2842-9736", "observed_orcids": ["https://orcid.org/0000-0002-2842-9736"]}, "institutions": [{"id": "https://openalex.org/I23075662", "display_name": "Taibah University", "ror": "https://ror.org/01xv1nn60", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I23075662"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Wael M.S. Yafooz", "raw_affiliation_strings": ["Faculty of Computer Science Department, College of Computer Science and Engineering, Taibah University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Faculty of Computer Science Department, College of Computer Science and Engineering, Taibah University", "institution_ids": ["https://openalex.org/I23075662"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5125287131", "display_name": "Nasser S. Albalawi", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I118590987", "display_name": "Northern Border University", "ror": "https://ror.org/03j9tzj20", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I118590987"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Nasser S. Albalawi", "raw_affiliation_strings": ["Department of Computer Science, Faculty of Computing and Information Technology, Northern Border University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science, Faculty of Computing and Information Technology, Northern Border University", "institution_ids": ["https://openalex.org/I118590987"]}]}], "abstract_inverted_index": {"In": [0, 180], "decentralized": [1, 50], "apps,": [2], "smart": [3, 16, 97, 247], "contracts": [4, 17], "are": [5, 18, 22, 61, 67, 102, 122], "used": [6, 69], "to": [7, 26, 30, 242], "conduct": [8], "trusted": [9], "transactions": [10], "on": [11], "the": [12, 35, 87, 120, 159, 164, 181, 190, 195, 240, 244], "Blockchain": [13], "(BC).": [14], "While": [15], "highly": [19, 24], "effective,": [20], "they": [21], "also": [23], "susceptible": [25], "security": [27, 245], "flaws,": [28], "leading": [29], "serious": [31], "financial": [32], "consequences.": [33], "However,": [34], "combination": [36], "of": [37, 89, 132, 167, 205, 211, 246], "BC": [38], "technology": [39], "and": [40, 49, 81, 104, 109, 130, 137, 151, 202, 213, 232], "artificial": [41], "intelligence": [42], "provides": [43], "a": [44, 112], "solution": [45], "for": [46, 91, 228], "powerful,": [47], "secure,": [48], "applications": [51], "in": [52, 70, 95, 158, 189], "various": [53, 71], "sectors.": [54], "Furthermore,": [55, 188], "large": [56], "language": [57, 82], "models": [58, 101, 121], "(LLMs),": [59], "which": [60, 217], "essential": [62], "advanced": [63], "machine": [64], "learning": [65], "frameworks,": [66], "now": [68], "applications,": [72], "including": [73, 116], "customer": [74], "service,": [75], "chatbots,": [76], "code": [77], "generation,": [78], "vulnerability": [79, 93, 118, 230], "detection,": [80, 231], "translation.": [83], "This": [84], "study": [85, 223], "investigates": [86], "use": [88], "LLMs": [90], "automated": [92], "detection": [94, 153], "Solidity-based": [96], "contracts.": [98, 248], "Specifically,": [99], "three": [100, 125], "evaluated": [103], "compared:": [105], "GPT-3.5-turbo,": [106], "DeepSeek": [107, 176, 208], "R1,": [108], "LLaMA-3.": [110], "With": [111], "labeled,": [113], "multi-class": [114], "dataset": [115], "four": [117], "types,": [119], "assessed": [123], "across": [124], "reasoning": [126], "strategies:": [127], "zero-shot,": [128], "few-shot,": [129], "chain": [131], "thought.": [133], "A": [134], "prompt-based": [135], "evaluation": [136, 226], "performance": [138, 198], "comparison": [139], "is": [140, 218], "conducted": [141], "using": [142], "standard": [143], "metrics": [144], "such": [145], "as": [146], "accuracy,": [147], "precision,": [148], "recall,": [149], "F1-score,": [150], "average": [152, 210], "time.": [154], "Results": [155], "show": [156], "that": [157, 236], "zero-shot": [160], "setting,": [161, 183, 192], "GPT-3.5-turbo": [162], "achieves": [163], "highest": [165], "accuracy": [166, 201], "94.59%,": [168], "followed": [169], "closely": [170], "by": [171], "LLaMA-3": [172, 184, 193], "with": [173, 199], "92%,": [174], "while": [175], "R1": [177], "achieved": [178], "78.95%.": [179], "few-shot": [182], "outperformed": [185], "other": [186], "models.": [187], "CoT": [191, 215], "demonstrates": [194], "strongest": [196], "overall": [197], "96%": [200], "an": [203, 225], "F1-score": [204], "0.82,": [206], "surpassing": [207], "R1's": [209], "78.95%": [212], "GPT-3.5's": [214], "performance,": [216], "notably": [219], "lower.": [220], "Hence,": [221], "this": [222], "develops": [224], "framework": [227], "LLM-based": [229], "we": [233], "have": [234], "demonstrated": [235], "prompt": [237], "engineering": [238], "has": [239], "potential": [241], "enhance": [243]}, "primary_topic": {"id": "https://openalex.org/T10270", "display_name": "Blockchain Technology Applications and Security", "score": 0.9574999809265137, "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/T10270", "display_name": "Blockchain Technology Applications and Security", "score": 0.9574999809265137, "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/T10260", "display_name": "Software Engineering Research", "score": 0.02419999986886978, "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/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.00430000014603138, "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": "doi:10.37965/jait.2025.0811", "is_oa": true, "landing_page_url": "https://doi.org/10.37965/jait.2025.0811", "pdf_url": "https://ojs.istp-press.com/jait/article/download/811/633", "source": {"id": "https://openalex.org/S4210177983", "display_name": "Journal of Artificial Intelligence and Technology", "issn_l": "2766-8649", "issn": ["2766-8649"], "is_oa": true, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "norway-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": "Journal of Artificial Intelligence and Technology", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4406725086", "doi": "https://doi.org/10.2196/preprints.71571", "title": "Self-Logical Consistency Assessment of Large Language Models for Patient Feedback Classification : Algorithm Development and Validation Study (Preprint)", "publication_year": 2025, "publication_date": "2025-01-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5116158420", "display_name": "Zeno Loi", "orcid": "https://orcid.org/0009-0000-3830-5297", "observed_orcids": ["https://orcid.org/0009-0000-3830-5297"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zeno Loi", "raw_affiliation_strings": [], "raw_orcid": "https://orcid.org/0009-0000-3830-5297", "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025083882", "display_name": "David Morquin", "orcid": "https://orcid.org/0000-0002-0757-0685", "observed_orcids": ["https://orcid.org/0000-0002-0757-0685"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "David Morquin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061533351", "display_name": "Fran\u00e7ois-Xavier Derzko", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fran\u00e7ois-Xavier Derzko", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5104602454", "display_name": "Xavier Corbier", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xavier Corbier", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Sylvie Gauthier", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sylvie Gauthier", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5045138456", "display_name": "Patrice Taourel", "orcid": "https://orcid.org/0000-0001-6465-1919", "observed_orcids": ["https://orcid.org/0000-0001-6465-1919"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Patrice Taourel", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5113291028", "display_name": "Emilie Prin-Lombardo", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Emilie Prin-Lombardo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5047333951", "display_name": "Gr\u00e9goire Mercier", "orcid": "https://orcid.org/0000-0001-5531-4515", "observed_orcids": ["https://orcid.org/0000-0001-5531-4515"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gr\u00e9goire Mercier", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5089576173", "display_name": "K\u00e9vin Yauy", "orcid": "https://orcid.org/0000-0001-6901-1670", "observed_orcids": ["https://orcid.org/0000-0001-6901-1670"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "K\u00e9vin Yauy", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"BACKGROUND": [0], "Patient": [1], "satisfaction": [2], "feedback": [3, 63, 111, 159, 221], "is": [4], "crucial": [5], "for": [6, 170, 174, 194, 218], "hospital": [7, 224], "service": [8, 225], "quality,": [9], "but": [10, 29], "manual": [11], "reviews": [12], "are": [13, 30], "time-consuming,": [14], "and": [15, 85, 94, 102, 116, 143, 172, 222], "traditional": [16], "natural": [17], "language": [18], "processing": [19], "methods": [20], "remain": [21], "inadequate.": [22], "Large": [23], "Language": [24], "Models": [25], "(LLMs)": [26], "show": [27], "promise": [28], "prone": [31], "to": [32, 49, 60, 113, 138, 147, 156, 181, 203], "extrinsic": [33], "faithfulness": [34], "hallucinations\u2014fabricated": [35], "or": [36, 208], "illogical": [37], "outputs": [38], "that": [39], "limit": [40], "their": [41], "reliability": [42, 65, 198], "in": [43, 199], "healthcare.": [44, 200], "OBJECTIVE": [45], "This": [46], "study": [47], "aimed": [48], "evaluate": [50], "the": [51, 81, 91, 157, 162], "Self-Logical": [52], "Consistency": [53], "Assessment": [54], "(SLCA),": [55], "an": [56], "original": [57, 92], "method": [58], "designed": [59], "enhance": [61, 204], "LLM": [62, 196], "classification": [64, 197], "by": [66], "enforcing": [67], "a": [68, 121, 190, 215], "logically-structured": [69], "chain": [70], "of": [71, 168], "thought.": [72], "METHODS": [73], "SLCA": [74, 99, 129, 164, 188], "uses": [75], "two": [76], "validation": [77], "steps:": [78], "self-consistency": [79], "(identifying": [80], "most": [82], "coherent": [83], "response)": [84], "logical": [86], "consistency": [87], "(ensuring": [88], "alignment": [89], "with": [90, 141, 150, 152], "statement": [93], "expert": [95], "classifications).": [96], "We": [97], "evaluated": [98], "using": [100], "GPT-4": [101, 142, 171], "Llama-3.1": [103], "405B": [104], "on": [105, 120], "12,600": [106], "classifications": [107], "from": [108, 125, 135, 144], "100": [109], "patient": [110, 220], "samples": [112], "assess": [114], "hallucinations,": [115], "tested": [117], "its": [118], "performance": [119, 184, 205], "49,140-classification": [122], "benchmark": [123], "derived": [124], "1,170": [126], "feedbacks.": [127], "RESULTS": [128], "reduced": [130], "hallucinations": [131], "among": [132], "detected": [133], "categories": [134], "15.80%": [136], "(168/1063)": [137], "0.51%": [139], "(4/786)": [140], "7.17%": [145], "(51/711)": [146], "1.67%": [148], "(10/599)": [149], "Llama-3.1,": [151], "residual": [153], "errors": [154], "confined": [155], "emergency": [158], "category.": [160], "On": [161], "benchmark,": [163], "achieved": [165], "precision-recall": [166], "scores": [167], "0.86-0.78": [169], "0.84-0.58": [173], "Llama-3.1.": [175], "These": [176], "results": [177], "demonstrate": [178], "SLCA\u2019s": [179], "ability": [180], "achieve": [182], "human-level": [183], "across": [185], "LLMs.": [186], "CONCLUSIONS": [187], "offers": [189], "scalable,": [191], "explainable": [192], "solution": [193], "improving": [195], "Its": [201], "capacity": [202], "without": [206], "fine-tuning": [207], "additional": [209], "training": [210], "data": [211], "positions": [212], "it": [213], "as": [214], "valuable": [216], "tool": [217], "analyzing": [219], "supporting": [223], "quality": [226], "improvement.": [227]}, "primary_topic": {"id": "https://openalex.org/T10664", "display_name": "Sentiment Analysis and Opinion Mining", "score": 0.8461999893188477, "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": 0.8461999893188477, "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": 0.07020000368356705, "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/T11722", "display_name": "Patient Satisfaction in Healthcare", "score": 0.02319999970495701, "subfield": {"id": "https://openalex.org/subfields/3600", "display_name": "General Health Professions"}, "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.71571", "is_oa": true, "landing_page_url": "https://doi.org/10.2196/preprints.71571", "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/W4417296930", "doi": "https://doi.org/10.48550/arxiv.2512.10756", "title": "OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification", "publication_year": 2025, "publication_date": "2025-12-11", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5075965565", "display_name": "Zijian Wu", "orcid": "https://orcid.org/0000-0002-6675-8231", "observed_orcids": ["https://orcid.org/0000-0002-6675-8231"]}, "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"]}, {"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN", "HK"], "is_corresponding": false, "raw_author_name": "Wu, Zijian", "raw_affiliation_strings": ["MMLab , The Chinese University of Hong Kong ,", "Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "MMLab , The Chinese University of Hong Kong ,", "institution_ids": ["https://openalex.org/I177725633"]}, {"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Kong, Lingkai", "orcid": null, "observed_orcids": []}, "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/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Kong, Lingkai", "raw_affiliation_strings": ["Shanghai AI Laboratory ,", "Shanghai Jiao Tong University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}, {"raw_affiliation_string": "Shanghai Jiao Tong University", "institution_ids": ["https://openalex.org/I183067930"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100709484", "display_name": "Wenwei Zhang", "orcid": "https://orcid.org/0000-0002-2748-4514", "observed_orcids": ["https://orcid.org/0000-0002-2748-4514"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhang, Wenwei", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109932574", "display_name": "Songyang Gao", "orcid": "https://orcid.org/0000-0001-5485-8019", "observed_orcids": ["https://orcid.org/0000-0001-5485-8019"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Gao, Songyang", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Gu, Yuzhe", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Gu, Yuzhe", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Cai, Zhongrui", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Cai, Zhongrui", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Ma, Tianyou", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ma, Tianyou", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100324598", "display_name": "Yuhong Liu", "orcid": "https://orcid.org/0000-0001-9364-0039", "observed_orcids": ["https://orcid.org/0000-0001-9364-0039"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Liu, Yuhong", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025948413", "display_name": "Zhi Wang", "orcid": "https://orcid.org/0000-0003-3398-9954", "observed_orcids": ["https://orcid.org/0000-0003-3398-9954", "https://orcid.org/0000-0003-4631-9669"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wang, Zhi", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007188271", "display_name": "Runyuan Ma", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ma, Runyuan", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100458579", "display_name": "Guangyu Wang", "orcid": "https://orcid.org/0000-0003-4803-7200", "observed_orcids": ["https://orcid.org/0000-0003-4803-7200"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wang, Guangyu", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Li, Wei", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Li, Wei", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101615091", "display_name": "Conghui He", "orcid": "https://orcid.org/0000-0001-8697-695X", "observed_orcids": ["https://orcid.org/0000-0001-8697-695X"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "He, Conghui", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010087030", "display_name": "Dahua Lin", "orcid": "https://orcid.org/0000-0002-8865-7896", "observed_orcids": ["https://orcid.org/0000-0002-8865-7896"]}, "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"]}, {"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN", "HK"], "is_corresponding": false, "raw_author_name": "Lin, Dahua", "raw_affiliation_strings": ["MMLab , The Chinese University of Hong Kong ,", "Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "MMLab , The Chinese University of Hong Kong ,", "institution_ids": ["https://openalex.org/I177725633"]}, {"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100437926", "display_name": "Kai Chen", "orcid": "https://orcid.org/0000-0001-6850-1723", "observed_orcids": ["https://orcid.org/0000-0001-6850-1723", "https://orcid.org/0000-0002-7665-7506", "https://orcid.org/0009-0000-7636-5848", "https://orcid.org/0000-0002-7233-5892"]}, "institutions": [{"id": "https://openalex.org/I4391012619", "display_name": "Shanghai Artificial Intelligence Laboratory", "ror": "https://ror.org/03wkvpx79", "country_code": "CN", "type": "facility", "lineage": ["https://openalex.org/I4391012619"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Chen, Kai", "raw_affiliation_strings": ["Shanghai AI Laboratory ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai AI Laboratory ,", "institution_ids": ["https://openalex.org/I4391012619"]}]}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2, 197], "(LLMs)": [3], "have": [4, 58], "achieved": [5], "significant": [6], "progress": [7], "in": [8, 45, 60, 64, 142], "solving": [9], "complex": [10, 66], "reasoning": [11, 48], "tasks": [12], "by": [13, 29, 70], "Reinforcement": [14], "Learning": [15], "with": [16, 126, 137, 201, 221, 226], "Verifiable": [17], "Rewards": [18], "(RLVR).": [19], "This": [20], "advancement": [21], "is": [22], "also": [23], "inseparable": [24], "from": [25, 100, 240], "the": [26, 41, 46, 65, 71, 78, 87, 94, 116, 132, 145, 150, 172, 236, 247], "oversight": [27], "automated": [28], "reliable": [30], "verifiers.": [31], "However,": [32], "current": [33, 54, 151], "outcome-based": [34], "verifiers": [35, 56], "(OVs)": [36], "are": [37, 154], "unable": [38], "to": [39, 77, 103, 129, 160, 208, 242], "inspect": [40], "unreliable": [42], "intermediate": [43], "steps": [44], "long": [47, 67, 101], "chains": [49], "of": [50, 73, 81, 97, 135, 149, 205, 238], "thought": [51], "(CoTs).": [52], "Meanwhile,": [53], "process-based": [55], "(PVs)": [57], "difficulties": [59], "reliably": [61], "detecting": [62], "errors": [63], "CoTs,": [68], "limited": [69], "scarcity": [72], "high-quality": [74], "annotations": [75, 128], "due": [76], "prohibitive": [79], "costs": [80], "human": [82], "annotations.": [83], "Therefore,": [84], "we": [85, 119], "propose": [86], "Outcome-based": [88], "Process": [89], "Verifier": [90], "(OPV),": [91], "which": [92], "verifies": [93], "rationale": [95], "process": [96], "summarized": [98], "outcomes": [99], "CoTs": [102], "achieve": [104], "both": [105], "accurate": [106], "and": [107, 110, 156, 169, 181], "efficient": [108], "verification": [109, 133], "enable": [111], "large-scale": [112], "annotation.": [113], "To": [114], "empower": [115], "proposed": [117], "verifier,": [118], "adopt": [120], "an": [121, 202], "iterative": [122], "active": [123], "learning": [124], "framework": [125], "expert": [127, 222], "progressively": [130], "improve": [131], "capability": [134], "OPV": [136, 153, 164, 211, 229], "fewer": [138], "annotation": [139], "costs.": [140], "Specifically,": [141], "each": [143], "iteration,": [144], "most": [146], "uncertain": [147], "cases": [148], "best": [152], "annotated": [155], "then": [157], "subsequently": [158], "used": [159], "train": [161], "a": [162], "new": [163, 186], "through": [165], "Rejection": [166], "Fine-Tuning": [167], "(RFT)": [168], "RLVR": [170], "for": [171], "next": [173], "round.": [174], "Extensive": [175], "experiments": [176], "demonstrate": [177], "OPV's": [178], "superior": [179], "performance": [180, 232], "broad": [182], "applicability.": [183], "It": [184], "achieves": [185], "state-of-the-art": [187], "results": [188], "on": [189, 244], "our": [190], "held-out": [191], "OPV-Bench,": [192], "outperforming": [193], "much": [194], "larger": [195], "open-source": [196], "such": [198], "as": [199, 246], "Qwen3-Max-Preview": [200], "F1": [203], "score": [204], "83.1": [206], "compared": [207], "76.3.": [209], "Furthermore,": [210], "effectively": [212], "detects": [213], "false": [214], "positives": [215], "within": [216], "synthetic": [217], "dataset,": [218], "closely": [219], "align": [220], "assessment.": [223], "When": [224], "collaborating": [225], "policy": [227], "models,": [228], "consistently": [230], "yields": [231], "gains,": [233], "e.g.,": [234], "raising": [235], "accuracy": [237], "DeepSeek-R1-Distill-Qwen-32B": [239], "55.2%": [241], "73.3%": [243], "AIME2025": [245], "compute": [248], "budget": [249], "scales.": [250]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.6098999977111816, "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": 0.6098999977111816, "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": 0.15160000324249268, "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": 0.06159999966621399, "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:2512.10756", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.10756", "pdf_url": "https://arxiv.org/pdf/2512.10756", "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/W4411294740", "doi": "https://doi.org/10.1142/s0218001425500193", "title": "LLM-Based Sensitive Data Recognition with Stepwise Chain-of-Thought Reasoning", "publication_year": 2025, "publication_date": "2025-06-13", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Honggang Wang", "orcid": "https://orcid.org/0009-0005-2330-0123", "observed_orcids": ["https://orcid.org/0009-0005-2330-0123"]}, "institutions": [{"id": "https://openalex.org/I17442442", "display_name": "State Grid Corporation of China (China)", "ror": "https://ror.org/05twwhs70", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I17442442"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Honggang Wang", "raw_affiliation_strings": ["Big Data Center, State Grid Co. of China Beijing, P. R. China"], "raw_orcid": "https://orcid.org/0009-0005-2330-0123", "affiliations": [{"raw_affiliation_string": "Big Data Center, State Grid Co. of China Beijing, P. R. China", "institution_ids": ["https://openalex.org/I17442442"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Shenglong Liu", "orcid": "https://orcid.org/0000-0002-7175-0138", "observed_orcids": ["https://orcid.org/0000-0002-7175-0138"]}, "institutions": [{"id": "https://openalex.org/I17442442", "display_name": "State Grid Corporation of China (China)", "ror": "https://ror.org/05twwhs70", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I17442442"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shenglong Liu", "raw_affiliation_strings": ["Big Data Center, State Grid Co. of China Beijing, P. R. China"], "raw_orcid": "https://orcid.org/0000-0002-7175-0138", "affiliations": [{"raw_affiliation_string": "Big Data Center, State Grid Co. of China Beijing, P. R. China", "institution_ids": ["https://openalex.org/I17442442"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5119268538", "display_name": "Yiwen Jiang", "orcid": "https://orcid.org/0009-0002-4626-4688", "observed_orcids": ["https://orcid.org/0009-0002-4626-4688"]}, "institutions": [{"id": "https://openalex.org/I17442442", "display_name": "State Grid Corporation of China (China)", "ror": "https://ror.org/05twwhs70", "country_code": "CN", "type": "company", "lineage": ["https://openalex.org/I17442442"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yiwen Jiang", "raw_affiliation_strings": ["Big Data Center, State Grid Co. of China Beijing, P. R. China"], "raw_orcid": "https://orcid.org/0009-0002-4626-4688", "affiliations": [{"raw_affiliation_string": "Big Data Center, State Grid Co. of China Beijing, P. R. China", "institution_ids": ["https://openalex.org/I17442442"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhenqi Guo", "orcid": "https://orcid.org/0009-0009-4289-8238", "observed_orcids": ["https://orcid.org/0009-0009-4289-8238"]}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhenqi Guo", "raw_affiliation_strings": ["School of Computer Science and Technology, Tongji University, Shanghai, P. R. China"], "raw_orcid": "https://orcid.org/0009-0009-4289-8238", "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Tongji University, Shanghai, P. R. China", "institution_ids": ["https://openalex.org/I116953780"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5042393592", "display_name": "Jiehao Tang", "orcid": "https://orcid.org/0000-0002-1496-552X", "observed_orcids": ["https://orcid.org/0000-0002-1496-552X"]}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jiehao Tang", "raw_affiliation_strings": ["School of Computer Science and Technology, Tongji University, Shanghai, P. R. China"], "raw_orcid": "https://orcid.org/0000-0002-1496-552X", "affiliations": [{"raw_affiliation_string": "School of Computer Science and Technology, Tongji University, Shanghai, P. R. China", "institution_ids": ["https://openalex.org/I116953780"]}]}], "abstract_inverted_index": {"Identifying": [0], "sensitive": [1, 33, 83], "text": [2, 84], "data": [3, 10, 34], "remains": [4], "a": [5, 28, 63, 93], "critical": [6], "challenge": [7], "for": [8, 31, 115], "industrial": [9, 122], "protection,": [11], "as": [12], "conventional": [13], "methods": [14], "lack": [15], "flexibility": [16], "and": [17, 74, 86, 117], "demand": [18], "extensive": [19], "manual": [20], "labeling.": [21], "While": [22], "Large": [23], "Language": [24], "Models": [25], "(LLMs)": [26], "offer": [27], "promising": [29], "avenue": [30], "automated": [32], "recognition": [35, 89], "(SDR),": [36], "their": [37, 76], "susceptibility": [38], "to": [39, 43, 68, 71, 79], "\u201challucination\u201d": [40], "often": [41], "leads": [42], "misclassification.": [44], "To": [45], "overcome": [46], "this,": [47], "we": [48], "introduce": [49], "an": [50], "LLM-based": [51], "SDR": [52, 109], "framework": [53], "powered": [54], "by": [55], "stepwise": [56], "Chain-of-Thought": [57], "(CoT)": [58], "reasoning.": [59], "Our": [60], "approach": [61], "employs": [62], "rigorously": [64], "designed": [65], "prompt": [66], "template": [67], "enable": [69], "LLMs": [70], "iteratively": [72], "reassess": [73], "refine": [75], "output,": [77], "leading": [78], "precise": [80], "identification": [81], "of": [82, 104], "positions": [85], "highly": [87], "fine-grained": [88], "results.": [90], "Experiments": [91], "on": [92], "real-world": [94], "dataset": [95], "from": [96], "the": [97, 101], "electric": [98], "sector": [99], "demonstrate": [100], "superior": [102], "performance": [103], "our": [105], "method": [106], "in": [107, 120], "domain-specific": [108], "tasks,": [110], "highlighting": [111], "its": [112], "strong": [113], "potential": [114], "robust": [116], "scalable": [118], "application": [119], "complex": [121], "environments.": [123]}, "primary_topic": {"id": "https://openalex.org/T10764", "display_name": "Privacy-Preserving Technologies in Data", "score": 0.8217999935150146, "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": 0.8217999935150146, "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": 0.12950000166893005, "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": 0.007600000128149986, "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:10.1142/s0218001425500193", "is_oa": false, "landing_page_url": "https://doi.org/10.1142/s0218001425500193", "pdf_url": null, "source": {"id": "https://openalex.org/S41486457", "display_name": "International Journal of Pattern Recognition and Artificial Intelligence", "issn_l": "0218-0014", "issn": ["0218-0014", "1793-6381"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-1", "norway-1"], "host_organization": "https://openalex.org/P4310319815", "host_organization_name": "World Scientific", "host_organization_lineage": ["https://openalex.org/P4310319815"], "host_organization_lineage_names": ["World Scientific"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal of Pattern Recognition and Artificial Intelligence", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W7106783047", "doi": null, "title": "Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect", "publication_year": 2025, "publication_date": "2025-11-24", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Wang, Yujing", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yujing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Hong, Weize", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hong, Weize", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"We": [0, 67, 92, 149], "present": [1], "a": [2, 85, 94, 119], "novel": [3], "framework": [4], "that": [5], "integrates": [6], "Large": [7], "Language": [8], "Models": [9], "(LLMs)": [10], "into": [11], "the": [12, 105], "Git": [13], "bisect": [14, 21, 51, 147], "process": [15], "for": [16, 75, 162], "semantic": [17, 43], "fault": [18], "localization.": [19], "Traditional": [20], "assumes": [22], "deterministic": [23], "predicates": [24], "and": [25, 42, 72, 78, 108, 138, 158], "binary": [26], "failure": [27], "states": [28], "assumptions": [29], "often": [30], "violated": [31], "in": [32, 104, 124, 145], "modern": [33], "software": [34], "development": [35], "due": [36], "to": [37, 98, 129, 133, 142], "flaky": [38], "tests,": [39], "nonmonotonic": [40], "regressions,": [41], "divergence": [44], "from": [45, 127], "upstream": [46], "repositories.": [47], "Our": [48], "system": [49], "augments": [50], "traversal": [52], "with": [53, 151], "structured": [54], "chain": [55], "of": [56, 88], "thought": [57], "reasoning,": [58, 155], "enabling": [59], "commit": [60, 62, 163], "by": [61, 139], "analysis": [63], "under": [64], "noisy": [65], "conditions.": [66], "evaluate": [68], "multiple": [69, 114], "open": [70, 115], "source": [71, 116], "proprietary": [73], "LLMs": [74], "their": [76], "suitability": [77], "fine": [79], "tune": [80], "DeepSeekCoderV2": [81], "using": [82], "QLoRA": [83], "on": [84, 153], "curated": [86], "dataset": [87], "semantically": [89], "labeled": [90], "diffs.": [91], "adopt": [93], "weak": [95], "supervision": [96], "workflow": [97], "reduce": [99], "annotation": [100], "overhead,": [101], "incorporating": [102], "human": [103], "loop": [106], "corrections": [107], "self": [109], "consistency": [110], "filtering.": [111], "Experiments": [112], "across": [113], "projects": [117], "show": [118], "6.4": [120], "point": [121], "absolute": [122], "gain": [123], "success": [125], "rate": [126], "74.2": [128], "80.6": [130], "percent,": [131], "leading": [132], "significantly": [134], "fewer": [135], "failed": [136], "traversals": [137], "experiment": [140], "up": [141], "2x": [143], "reduction": [144], "average": [146], "time.": [148], "conclude": [150], "discussions": [152], "temporal": [154], "prompt": [156], "design,": [157], "finetuning": [159], "strategies": [160], "tailored": [161], "level": [164], "behavior": [165], "analysis.": [166]}, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.6474999785423279, "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": 0.6474999785423279, "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/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.34860000014305115, "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"}}, {"id": "https://openalex.org/T12127", "display_name": "Software System Performance and Reliability", "score": 0.001500000013038516, "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"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2511.18854", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.18854", "pdf_url": "https://arxiv.org/pdf/2511.18854", "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/W4414585765", "doi": "https://doi.org/10.48550/arxiv.2505.19255", "title": "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use", "publication_year": 2025, "publication_date": "2025-05-25", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101970159", "display_name": "Mingyuan Wu", "orcid": "https://orcid.org/0009-0006-5203-7843", "observed_orcids": ["https://orcid.org/0009-0006-5203-7843", "https://orcid.org/0009-0008-6803-7797"]}, "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": "Wu, Mingyuan", "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/A5015366882", "display_name": "Jingcheng Yang", "orcid": "https://orcid.org/0009-0003-7081-1562", "observed_orcids": ["https://orcid.org/0009-0003-7081-1562"]}, "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": "Yang, Jingcheng", "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/A5111346128", "display_name": "Jize Jiang", "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": "Jiang, Jize", "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/A5100780133", "display_name": "Minglei Li", "orcid": "https://orcid.org/0000-0001-5432-2855", "observed_orcids": ["https://orcid.org/0000-0001-5432-2855", "https://orcid.org/0000-0002-1359-7809"]}, "institutions": [{"id": "https://openalex.org/I27837315", "display_name": "University of Michigan", "ror": "https://ror.org/00jmfr291", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I27837315"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Li, Meitang", "raw_affiliation_strings": ["University of Michigan Ann Arbor ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Michigan Ann Arbor ,", "institution_ids": ["https://openalex.org/I27837315"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Yan, Kaizhuo", "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": "Yan, Kaizhuo", "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/A5028988765", "display_name": "Hanchao Yu", "orcid": "https://orcid.org/0009-0000-4407-7796", "observed_orcids": ["https://orcid.org/0009-0000-4407-7796"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yu, Hanchao", "raw_affiliation_strings": ["Independent Researcher"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Independent Researcher", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5077768924", "display_name": "Minjia Zhang", "orcid": "https://orcid.org/0000-0002-8165-166X", "observed_orcids": ["https://orcid.org/0000-0002-8165-166X"]}, "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": "Zhang, Minjia", "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/A5028518494", "display_name": "ChengXiang Zhai", "orcid": "https://orcid.org/0000-0002-6434-3702", "observed_orcids": ["https://orcid.org/0000-0002-6434-3702"]}, "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": "Zhai, Chengxiang", "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/A5074224097", "display_name": "Klara Nahrstedt", "orcid": "https://orcid.org/0000-0001-6813-3043", "observed_orcids": ["https://orcid.org/0000-0001-6813-3043"]}, "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": "Nahrstedt, Klara", "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"]}]}], "abstract_inverted_index": {"Reinforcement": [0], "Learning": [1], "Finetuning": [2], "(RFT)": [3], "has": [4], "significantly": [5], "advanced": [6], "the": [7, 55, 74, 101], "reasoning": [8, 42, 53, 92, 114, 136, 156], "capabilities": [9], "of": [10, 19, 50, 84, 169], "large": [11], "language": [12], "models": [13, 35], "(LLMs)": [14], "by": [15, 86, 158], "enabling": [16, 104], "long": [17], "chains": [18, 83], "thought,": [20], "self-correction,": [21], "and": [22, 89, 109, 150, 165], "effective": [23], "tool": [24, 133], "use.": [25], "While": [26], "recent": [27], "works": [28], "attempt": [29], "to": [30, 33, 80, 106, 111, 125, 161], "extend": [31], "RFT": [32, 102], "vision-language": [34], "(VLMs),": [36], "these": [37], "efforts": [38], "largely": [39], "produce": [40], "text-only": [41], "conditioned": [43], "on": [44, 139, 143], "static": [45], "image": [46], "inputs,": [47], "falling": [48], "short": [49], "true": [51], "multimodal": [52, 82, 167], "in": [54, 177], "response.": [56], "In": [57], "contrast,": [58], "test-time": [59], "methods": [60], "like": [61], "Visual": [62], "Sketchpad": [63], "incorporate": [64], "visual": [65, 91, 97, 113, 132, 145], "steps": [66, 115], "but": [67], "lack": [68], "training": [69], "mechanisms.": [70], "We": [71], "introduce": [72], "VTool-R1,": [73], "first": [75], "framework": [76], "that": [77, 116, 153], "trains": [78], "VLMs": [79, 105, 160], "generate": [81, 112, 166], "thought": [85], "interleaving": [87], "text": [88], "intermediate": [90], "steps.": [93], "VTool-R1": [94, 154], "integrates": [95], "Python-based": [96], "editing": [98], "tools": [99], "into": [100], "process,": [103], "learn": [107], "when": [108], "how": [110], "benefit": [117], "final": [118], "reasoning.": [119], "Trained": [120], "with": [121, 163, 171], "outcome-based": [122], "rewards": [123], "tied": [124], "task": [126], "accuracy,": [127], "our": [128, 183], "approach": [129], "elicits": [130], "strategic": [131], "use": [134], "for": [135], "without": [137], "relying": [138], "process-based": [140], "supervision.": [141], "Experiments": [142], "structured": [144], "question": [146], "answering": [147], "over": [148], "charts": [149], "tables": [151], "show": [152], "enhances": [155], "performance": [157], "teaching": [159], "\"think": [162], "images\"": [164], "chain": [168], "thoughts": [170], "tools.": [172], "To": [173], "support": [174], "future": [175], "research": [176], "multi-turn": [178], "multi-modal": [179], "reasoning,": [180], "we": [181], "open-source": [182], "code": [184], "at": [185], "https://github.com/VTOOL-R1/vtool-r1": [186]}, "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/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/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:2505.19255", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.19255", "pdf_url": "https://arxiv.org/pdf/2505.19255", "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/W4414631014", "doi": "https://doi.org/10.48550/arxiv.2504.15466", "title": "Learning Adaptive Parallel Reasoning with Language Models", "publication_year": 2025, "publication_date": "2025-04-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5103512739", "display_name": "Jiayi Pan", "orcid": "https://orcid.org/0009-0007-0468-4592", "observed_orcids": ["https://orcid.org/0009-0007-0468-4592"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Pan, Jiayi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5005099833", "display_name": "Xiuyu Li", "orcid": "https://orcid.org/0009-0000-0204-8057", "observed_orcids": ["https://orcid.org/0009-0000-0204-8057"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Xiuyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114232525", "display_name": "Long Lian", "orcid": "https://orcid.org/0000-0001-6098-189X", "observed_orcids": ["https://orcid.org/0000-0001-6098-189X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lian, Long", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5052858739", "display_name": "Charlie Snell", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Snell, Charlie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100645656", "display_name": "Yifei Zhou", "orcid": "https://orcid.org/0000-0002-2176-9316", "observed_orcids": ["https://orcid.org/0000-0002-2176-9316", "https://orcid.org/0000-0002-6372-8205", "https://orcid.org/0009-0004-6960-8281"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhou, Yifei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5084801169", "display_name": "Adam Yala", "orcid": "https://orcid.org/0000-0001-9576-2590", "observed_orcids": ["https://orcid.org/0000-0001-9576-2590"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yala, Adam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5029105520", "display_name": "Trevor J. Darrell", "orcid": "https://orcid.org/0000-0001-5453-8533", "observed_orcids": ["https://orcid.org/0000-0001-5453-8533"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Darrell, Trevor", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5047285420", "display_name": "Kurt Keutzer", "orcid": "https://orcid.org/0000-0003-3868-8501", "observed_orcids": ["https://orcid.org/0000-0003-3868-8501"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Keutzer, Kurt", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5009625151", "display_name": "Alane Suhr", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Suhr, Alane", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Scaling": [0], "inference-time": [1], "computation": [2, 148], "has": [3], "substantially": [4], "improved": [5, 157], "the": [6, 120, 133], "reasoning": [7, 63, 80, 116, 122, 180], "capabilities": [8], "of": [9, 127, 185], "language": [10, 67, 174], "models.": [11], "However,": [12], "existing": [13, 79], "methods": [14, 35, 81], "have": [15], "significant": [16, 125], "limitations:": [17], "serialized": [18, 72], "chain-of-thought": [19], "approaches": [20], "generate": [21], "overly": [22], "long": [23], "outputs,": [24], "leading": [25], "to": [26, 69, 108, 176], "increased": [27, 147], "latency": [28, 161], "and": [29, 47, 73, 89, 104], "exhausted": [30], "context": [31, 135], "windows,": [32], "while": [33], "parallel": [34, 74], "such": [36], "as": [37], "self-consistency": [38], "suffer": [39], "from": [40], "insufficient": [41], "coordination,": [42], "resulting": [43], "in": [44], "redundant": [45], "computations": [46, 75], "limited": [48], "performance": [49, 131], "gains.": [50], "To": [51], "address": [52], "these": [53], "shortcomings,": [54], "we": [55], "propose": [56], "Adaptive": [57], "Parallel": [58], "Reasoning": [59], "(APR),": [60], "a": [61, 170], "novel": [62], "framework": [64], "that": [65], "enables": [66], "models": [68, 175], "orchestrate": [70], "both": [71, 102], "end-to-end.": [76], "APR": [77, 168], "generalizes": [78], "by": [82], "enabling": [83, 173], "adaptive": [84, 183], "multi-threaded": [85], "inference": [86, 106], "using": [87], "spawn()": [88], "join()": [90], "operations.": [91], "A": [92], "key": [93], "innovation": [94], "is": [95], "our": [96], "end-to-end": [97], "reinforcement": [98], "learning": [99], "strategy,": [100], "optimizing": [101], "parent": [103], "child": [105], "threads": [107], "enhance": [109], "task": [110, 123], "success": [111], "rate": [112], "without": [113], "requiring": [114], "predefined": [115], "structures.": [117], "Experiments": [118], "on": [119], "Countdown": [121], "demonstrate": [124], "benefits": [126], "APR:": [128], "(1)": [129], "higher": [130], "within": [132], "same": [134], "window": [136], "(83.4%": [137], "vs.": [138, 150, 163], "60.0%": [139], "at": [140, 152, 159, 165], "4k": [141], "context);": [142], "(2)": [143], "superior": [144], "scalability": [145], "with": [146], "(80.1%": [149], "66.6%": [151], "20k": [153], "total": [154], "tokens);": [155], "(3)": [156], "accuracy": [158], "equivalent": [160], "(75.2%": [162], "57.3%": [164], "approximately": [166], "5,000ms).": [167], "represents": [169], "step": [171], "towards": [172], "autonomously": [177], "optimize": [178], "their": [179], "processes": [181], "through": [182], "allocation": [184], "computation.": [186]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.6439999938011169, "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": 0.6439999938011169, "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": 0.2930000126361847, "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/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.008200000040233135, "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:2504.15466", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.15466", "pdf_url": "https://arxiv.org/pdf/2504.15466", "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/W4407571503", "doi": "https://doi.org/10.48550/arxiv.2502.08991", "title": "Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?", "publication_year": 2025, "publication_date": "2025-02-13", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5023506063", "display_name": "Amirhesam Abedsoltan", "orcid": "https://orcid.org/0009-0002-3816-8856", "observed_orcids": ["https://orcid.org/0009-0002-3816-8856"]}, "institutions": [{"id": "https://openalex.org/I36258959", "display_name": "University of California San Diego", "ror": "https://ror.org/0168r3w48", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I36258959"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Abedsoltan, Amirhesam", "raw_affiliation_strings": ["Department of Computer Science and Engineering , UC San Diego"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering , UC San Diego", "institution_ids": ["https://openalex.org/I36258959"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042509817", "display_name": "Huaqing Zhang", "orcid": "https://orcid.org/0000-0001-9180-7309", "observed_orcids": ["https://orcid.org/0000-0001-9180-7309"]}, "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": "Zhang, Huaqing", "raw_affiliation_strings": ["Institute for Interdisciplinary In- formation Sciences , Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Interdisciplinary In- formation Sciences , Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5008378675", "display_name": "Kaiyue Wen", "orcid": "https://orcid.org/0009-0002-9168-1851", "observed_orcids": ["https://orcid.org/0009-0002-9168-1851"]}, "institutions": [{"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": "Wen, Kaiyue", "raw_affiliation_strings": ["Stanford University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Stanford University", "institution_ids": ["https://openalex.org/I97018004"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Lin, Hongzhou", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lin, Hongzhou", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5064766573", "display_name": "Jingzhao Zhang", "orcid": "https://orcid.org/0000-0002-4347-2361", "observed_orcids": ["https://orcid.org/0000-0002-4347-2361"]}, "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": "Zhang, Jingzhao", "raw_affiliation_strings": ["Institute for Interdisciplinary In- formation Sciences , Tsinghua University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Interdisciplinary In- formation Sciences , Tsinghua University", "institution_ids": ["https://openalex.org/I99065089"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5102796459", "display_name": "Mikhail Belkin", "orcid": "https://orcid.org/0009-0005-8633-3926", "observed_orcids": ["https://orcid.org/0009-0005-8633-3926"]}, "institutions": [{"id": "https://openalex.org/I36258959", "display_name": "University of California San Diego", "ror": "https://ror.org/0168r3w48", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I36258959"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Belkin, Mikhail", "raw_affiliation_strings": ["Department of Computer Science and Engineering , UC San Diego", "Halicioglu Data Science Institute , UC San Diego"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Engineering , UC San Diego", "institution_ids": ["https://openalex.org/I36258959"]}, {"raw_affiliation_string": "Halicioglu Data Science Institute , UC San Diego", "institution_ids": ["https://openalex.org/I36258959"]}]}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2], "(LLMs)": [3], "exhibit": [4], "remarkable": [5], "task": [6, 39, 46, 57, 109], "generalization,": [7], "solving": [8], "tasks": [9, 34, 91], "they": [10], "were": [11], "never": [12], "explicitly": [13], "trained": [14], "on": [15, 97, 111], "with": [16], "only": [17, 98], "a": [18, 23, 30, 37, 59, 69, 77], "few": [19], "demonstrations.": [20], "This": [21, 75], "raises": [22], "fundamental": [24], "question:": [25], "When": [26], "can": [27], "learning": [28], "from": [29], "small": [31], "set": [32], "of": [33, 51, 61, 72, 80], "generalize": [35], "to": [36, 88], "large": [38], "family?": [40], "In": [41], "this": [42], "paper,": [43], "we": [44, 102], "investigate": [45], "generalization": [47, 87, 110, 126], "through": [48], "the": [49], "lens": [50], "autoregressive": [52], "compositional": [53], "structure,": [54], "where": [55], "each": [56, 65], "is": [58, 67, 92], "composition": [60], "$T$": [62], "operations,": [63], "and": [64, 119, 129], "operation": [66], "among": [68], "finite": [70], "family": [71], "$D$": [73], "subtasks.": [74], "yields": [76], "total": [78], "class": [79], "size": [81], "$D^T$.": [82], "We": [83, 123], "first": [84], "show": [85, 125], "that": [86, 104], "all": [89], "$D^T$": [90], "theoretically": [93], "achievable": [94], "by": [95], "training": [96], "$\\widetilde{O}(D)$": [99], "tasks.": [100], "Empirically,": [101], "demonstrate": [103], "Transformers": [105], "achieve": [106], "such": [107], "exponential": [108], "sparse": [112], "parity": [113, 132], "functions": [114], "via": [115], "In-context": [116], "Learning": [117], "(ICL)": [118], "chain-of-thought": [120], "(CoT)": [121], "reasoning.": [122], "further": [124], "in": [127], "arithmetic": [128], "translation,": [130], "beyond": [131], "functions.": [133]}, "primary_topic": {"id": "https://openalex.org/T11307", "display_name": "Domain Adaptation and Few-Shot Learning", "score": 0.6255000233650208, "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": 0.6255000233650208, "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": 0.2971000075340271, "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": 0.026100000366568565, "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:2502.08991", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.08991", "pdf_url": "https://arxiv.org/pdf/2502.08991", "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/W4410974031", "doi": "https://doi.org/10.1007/s44267-025-00079-w", "title": "SHIELD: an evaluation benchmark for face spoofing and forgery detection with multimodal large language models", "publication_year": 2025, "publication_date": "2025-06-03", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102159687", "display_name": "Yichen Shi", "orcid": "https://orcid.org/0009-0001-9749-7855", "observed_orcids": ["https://orcid.org/0009-0001-9749-7855"]}, "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"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yichen Shi", "raw_affiliation_strings": ["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200030, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200030, China", "institution_ids": ["https://openalex.org/I183067930"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101836448", "display_name": "Yuhao Gao", "orcid": "https://orcid.org/0000-0001-9569-572X", "observed_orcids": ["https://orcid.org/0000-0001-9569-572X"]}, "institutions": [{"id": "https://openalex.org/I90090648", "display_name": "Shijiazhuang Tiedao University", "ror": "https://ror.org/022e9e065", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I90090648"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuhao Gao", "raw_affiliation_strings": ["School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China", "institution_ids": ["https://openalex.org/I90090648"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061194131", "display_name": "Yingxin Lai", "orcid": "https://orcid.org/0000-0003-1369-2205", "observed_orcids": ["https://orcid.org/0000-0003-1369-2205"]}, "institutions": [{"id": "https://openalex.org/I191208505", "display_name": "Xiamen University", "ror": "https://ror.org/00mcjh785", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I191208505"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yingxin Lai", "raw_affiliation_strings": ["Department of Artificial Intelligence, Xiamen University, Xiamen, 361005, Fujian, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Artificial Intelligence, Xiamen University, Xiamen, 361005, Fujian, China", "institution_ids": ["https://openalex.org/I191208505"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100764451", "display_name": "Hongyang Wang", "orcid": "https://orcid.org/0000-0003-4544-0715", "observed_orcids": ["https://orcid.org/0000-0003-4544-0715"]}, "institutions": [{"id": "https://openalex.org/I90090648", "display_name": "Shijiazhuang Tiedao University", "ror": "https://ror.org/022e9e065", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I90090648"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hongyang Wang", "raw_affiliation_strings": ["School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China", "institution_ids": ["https://openalex.org/I90090648"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100876533", "display_name": "Jun Zong Feng", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I90090648", "display_name": "Shijiazhuang Tiedao University", "ror": "https://ror.org/022e9e065", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I90090648"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jun Feng", "raw_affiliation_strings": ["School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, 050043, China", "institution_ids": ["https://openalex.org/I90090648"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100317887", "display_name": "Lei He", "orcid": "https://orcid.org/0000-0002-8615-5673", "observed_orcids": ["https://orcid.org/0000-0002-8615-5673"]}, "institutions": [{"id": "https://openalex.org/I161318765", "display_name": "University of California, Los Angeles", "ror": "https://ror.org/046rm7j60", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I161318765"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Lei He", "raw_affiliation_strings": ["Electrical Engineering Department, UCLA, Los Angeles, CA, 90095, United States of America"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Electrical Engineering Department, UCLA, Los Angeles, CA, 90095, United States of America", "institution_ids": ["https://openalex.org/I161318765"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5063979916", "display_name": "Jun Wan", "orcid": "https://orcid.org/0000-0002-4735-2885", "observed_orcids": ["https://orcid.org/0000-0002-4735-2885"]}, "institutions": [{"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/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"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jun Wan", "raw_affiliation_strings": ["New Laboratory of Pattern Recognition(NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "New Laboratory of Pattern Recognition(NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China", "institution_ids": ["https://openalex.org/I19820366", "https://openalex.org/I4210112150"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100751850", "display_name": "Changsheng Chen", "orcid": "https://orcid.org/0000-0003-4857-6810", "observed_orcids": ["https://orcid.org/0000-0003-4857-6810"]}, "institutions": [{"id": "https://openalex.org/I180726961", "display_name": "Shenzhen University", "ror": "https://ror.org/01vy4gh70", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I180726961"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Changsheng Chen", "raw_affiliation_strings": ["College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China", "institution_ids": ["https://openalex.org/I180726961"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103099781", "display_name": "Zitong Yu", "orcid": "https://orcid.org/0000-0003-0422-6616", "observed_orcids": ["https://orcid.org/0000-0003-0422-6616"]}, "institutions": [{"id": "https://openalex.org/I4396570619", "display_name": "Great Bay University", "ror": "https://ror.org/01hdgge16", "country_code": null, "type": "education", "lineage": ["https://openalex.org/I4396570619"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Zitong Yu", "raw_affiliation_strings": ["School of Computing and Information Technology, Great Bay University, Dongguan, Guangdong, 523000, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Computing and Information Technology, Great Bay University, Dongguan, Guangdong, 523000, China", "institution_ids": ["https://openalex.org/I4396570619"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5068837264", "display_name": "Xiaochun Cao", "orcid": "https://orcid.org/0000-0001-7141-708X", "observed_orcids": ["https://orcid.org/0000-0001-7141-708X"]}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiaochun Cao", "raw_affiliation_strings": ["School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, China", "institution_ids": ["https://openalex.org/I157773358"]}]}], "abstract_inverted_index": {"Abstract": [0], "Multimodal": [1], "large": [2], "language": [3], "models": [4], "(MLLMs)": [5], "have": [6], "demonstrated": [7], "strong": [8, 157], "capabilities": [9], "in": [10, 33, 117], "vision-related": [11], "tasks,": [12], "capitalizing": [13], "on": [14, 69], "their": [15, 23], "visual": [16, 28, 107], "semantic": [17], "comprehension": [18], "and": [19, 30, 55, 62, 88, 103, 108, 114, 119, 138, 142], "reasoning": [20], "capabilities.": [21], "However,": [22], "ability": [24], "to": [25, 49, 65], "detect": [26], "subtle": [27], "spoofing": [29, 54], "forgery": [31, 56, 97], "clues": [32], "face": [34, 53, 71, 78, 96, 146], "attack": [35, 92], "detection": [36, 98], "tasks": [37], "remains": [38], "underexplored.": [39], "In": [40], "this": [41, 151], "paper,": [42], "we": [43, 59, 81, 100, 126], "introduce": [44], "a": [45, 128], "benchmark,": [46], "SHIELD": [47], ",": [48], "evaluate": [50, 82, 101], "MLLMs": [51, 155], "for": [52, 136, 159], "detection.": [57], "Specifically,": [58], "design": [60], "true/false": [61], "multiple-choice": [63], "questions": [64], "assess": [66], "MLLM": [67], "performance": [68], "multimodal": [70], "data": [72], "across": [73], "two": [74], "tasks.": [75], "For": [76, 94], "the": [77, 95, 161, 165], "anti-spoofing": [79], "task,": [80, 99], "three": [83], "modalities": [84], "(i.e.,": [85], "RGB,": [86], "infrared,": [87], "depth)": [89], "under": [90], "six": [91], "types.": [93], "GAN-based": [102], "diffusion-based": [104], "data,": [105], "incorporating": [106], "acoustic": [109], "modalities.": [110], "We": [111], "conduct": [112], "zero-shot": [113], "few-shot": [115], "evaluations": [116], "standard": [118], "chain": [120, 131], "of": [121, 132, 145, 150, 167], "thought": [122, 133], "(COT)": [123], "settings.": [124], "Additionally,": [125], "propose": [127], "novel": [129], "multi-attribute": [130], "(MA-COT)": [134], "paradigm": [135], "describing": [137], "judging": [139], "various": [140], "task-specific": [141], "task-irrelevant": [143], "attributes": [144], "images.": [147], "The": [148], "findings": [149], "study": [152], "demonstrate": [153], "that": [154], "exhibit": [156], "potential": [158], "addressing": [160], "challenges": [162], "associated": [163], "with": [164], "security": [166], "facial": [168], "recognition": [169], "technology": [170], "applications.": [171]}, "primary_topic": {"id": "https://openalex.org/T12357", "display_name": "Digital Media Forensic Detection", "score": 0.576200008392334, "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/T12357", "display_name": "Digital Media Forensic Detection", "score": 0.576200008392334, "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/T10828", "display_name": "Biometric Identification and Security", "score": 0.28540000319480896, "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/T11448", "display_name": "Face recognition and analysis", "score": 0.11879999935626984, "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:10.1007/s44267-025-00079-w", "is_oa": true, "landing_page_url": "https://doi.org/10.1007/s44267-025-00079-w", "pdf_url": "https://link.springer.com/content/pdf/10.1007/s44267-025-00079-w.pdf", "source": {"id": "https://openalex.org/S4387289164", "display_name": "Visual Intelligence", "issn_l": "2731-9008", "issn": ["2731-9008", "2097-3330"], "is_oa": true, "is_in_doaj": true, "is_core": true, "listed_in": ["cwts-core", "doaj", "jufo-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": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Visual Intelligence", "raw_type": "journal-article"}, "cited_by_count": 24, "is_retracted": false}, {"id": "https://openalex.org/W4417104745", "doi": "https://doi.org/10.48550/arxiv.2510.11718", "title": "CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images", "publication_year": 2025, "publication_date": "2025-10-13", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5054320268", "display_name": "Chengqi Duan", "orcid": "https://orcid.org/0009-0004-5737-019X", "observed_orcids": ["https://orcid.org/0009-0004-5737-019X"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Duan, Chengqi", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101853880", "display_name": "Kaiyue Sun", "orcid": "https://orcid.org/0000-0003-1401-4051", "observed_orcids": ["https://orcid.org/0000-0003-1401-4051"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Sun, Kaiyue", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5025456709", "display_name": "Rongyao Fang", "orcid": "https://orcid.org/0000-0002-8010-4808", "observed_orcids": ["https://orcid.org/0000-0002-8010-4808"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Fang, Rongyao", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5012273415", "display_name": "Manyuan Zhang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Zhang, Manyuan", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061181883", "display_name": "Feng Yan", "orcid": "https://orcid.org/0000-0003-1841-0318", "observed_orcids": ["https://orcid.org/0000-0003-1841-0318"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Feng, Yan", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5083405649", "display_name": "Ying Luo", "orcid": "https://orcid.org/0000-0003-3074-8813", "observed_orcids": ["https://orcid.org/0000-0003-3074-8813", "https://orcid.org/0000-0003-1460-4289"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Luo, Ying", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Liu, Yufang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Liu, Yufang", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101645620", "display_name": "Ke Wang", "orcid": "https://orcid.org/0000-0001-5783-1655", "observed_orcids": ["https://orcid.org/0000-0001-5783-1655"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Wang, Ke", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Pei, Peng", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Pei, Peng", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5068562468", "display_name": "Xunliang Cai", "orcid": "https://orcid.org/0000-0003-0685-9556", "observed_orcids": ["https://orcid.org/0000-0003-0685-9556"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Cai, Xunliang", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100732450", "display_name": "Hongsheng Li", "orcid": "https://orcid.org/0000-0002-2664-7975", "observed_orcids": ["https://orcid.org/0000-0002-2664-7975"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Li, Hongsheng", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Ma, Yi", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Ma, Yi", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5027234036", "display_name": "Xihui Liu", "orcid": "https://orcid.org/0000-0002-1791-8745", "observed_orcids": ["https://orcid.org/0000-0002-1791-8745", "https://orcid.org/0000-0003-1831-9952"]}, "institutions": [{"id": "https://openalex.org/I889458895", "display_name": "University of Hong Kong", "ror": "https://ror.org/02zhqgq86", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I889458895"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Liu, Xihui", "raw_affiliation_strings": ["CUHK LLM/VLM"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "CUHK LLM/VLM", "institution_ids": ["https://openalex.org/I889458895"]}]}], "abstract_inverted_index": {"Recent": [0], "advances": [1], "in": [2, 16, 87], "Large": [3], "Language": [4, 9], "Models": [5, 10], "(LLMs)": [6], "and": [7, 45, 62, 68, 129, 212, 223, 238], "Vision": [8], "(VLMs)": [11], "have": [12], "shown": [13], "significant": [14], "progress": [15], "mathematical": [17, 115, 156, 172, 210], "reasoning,": [18], "yet": [19], "they": [20], "still": [21], "face": [22], "a": [23, 79, 148, 205], "critical": [24], "bottleneck": [25], "with": [26, 85, 134, 216], "problems": [27, 133], "requiring": [28], "visual": [29], "assistance,": [30], "such": [31, 71, 227], "as": [32, 98, 100, 110], "drawing": [33], "auxiliary": [34], "lines": [35], "or": [36], "plotting": [37, 102], "functions": [38], "to": [39, 49, 94, 113, 141, 182], "solve": [40, 114], "the": [41, 65, 92, 124, 167, 194, 214, 217], "problems.": [42, 116, 173, 228], "Most": [43], "LLMs": [44], "VLMs": [46], "are": [47], "constrained": [48], "text-only": [50], "reasoning": [51, 97, 200, 211], "chains,": [52], "while": [53], "multimodal": [54, 209], "unified": [55], "models": [56, 240], "that": [57, 177], "can": [58], "generate": [59, 95], "interleaved": [60], "text": [61, 96], "images": [63, 109], "lack": [64], "necessary": [66], "precision": [67], "controllability": [69], "for": [70, 83, 131, 153, 170, 208, 226], "tasks.": [72], "To": [73, 117, 229], "address": [74], "this,": [75, 119], "we": [76, 120, 146, 165, 233], "propose": [77], "CodePlot-CoT,": [78], "code-driven": [80, 199], "Chain-of-Thought": [81], "paradigm": [82], "\"thinking": [84], "images\"": [86], "mathematics.": [88], "Our": [89, 202], "approach": [90, 225], "leverages": [91], "VLM": [93], "well": [99], "executable": [101], "code,": [103, 237], "which": [104], "is": [105], "then": [106], "rendered": [107], "into": [108, 158], "\"visual": [111], "thought\",": [112], "achieve": [118], "first": [121, 125, 218], "construct": [122], "Math-VR,": [123], "large-scale,": [126], "bilingual": [127], "dataset": [128], "benchmark": [130], "Mathematics": [132], "Visual": [135], "Reasoning,": [136], "comprising": [137], "178K": [138], "samples.": [139], "Second,": [140], "create": [142], "high-quality": [143], "training": [144, 163], "data,": [145, 164], "develop": [147], "state-of-the-art": [149], "image-to-code": [150], "converter": [151], "specialized": [152], "parsing": [154], "complex": [155], "figures": [157], "codes.": [159], "Finally,": [160], "using": [161], "these": [162], "train": [166], "CodePlot-CoT": [168], "model": [169, 179, 187], "solving": [171], "Experimental": [174], "results": [175], "show": [176], "our": [178, 189, 197, 235], "achieves": [180], "up": [181], "21%": [183], "increase": [184], "over": [185], "base": [186], "on": [188], "new": [190, 206], "benchmark,": [191, 222], "fully": [192], "validating": [193], "efficacy": [195], "of": [196], "proposed": [198], "paradigm.": [201], "work": [203], "opens": [204], "direction": [207], "provides": [213], "community": [215], "large-scale": [219], "dataset,": [220], "comprehensive": [221], "strong": [224], "facilitate": [230], "future": [231], "research,": [232], "make": [234], "datasets,": [236], "pretrained": [239], "publicly": [241], "available": [242], "at": [243], "https://github.com/HKU-MMLab/Math-VR-CodePlot-CoT.": [244]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9589999914169312, "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": 0.9589999914169312, "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/T13523", "display_name": "Mathematics, Computing, and Information Processing", "score": 0.01549999974668026, "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/T12522", "display_name": "Mathematics Education and Pedagogy", "score": 0.007499999832361937, "subfield": {"id": "https://openalex.org/subfields/2604", "display_name": "Applied Mathematics"}, "field": {"id": "https://openalex.org/fields/26", "display_name": "Mathematics"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2510.11718", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.11718", "pdf_url": "https://arxiv.org/pdf/2510.11718", "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/W4416966043", "doi": "https://doi.org/10.48550/arxiv.2512.01559", "title": "LLM2Fx-Tools: Tool Calling For Music Post-Production", "publication_year": 2025, "publication_date": "2025-12-01", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5010952526", "display_name": "SeungHeon Doh", "orcid": "https://orcid.org/0000-0002-8448-9928", "observed_orcids": ["https://orcid.org/0000-0002-8448-9928"]}, "institutions": [{"id": "https://openalex.org/I157485424", "display_name": "Korea Advanced Institute of Science and Technology", "ror": "https://ror.org/05apxxy63", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I157485424"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Doh, Seungheon", "raw_affiliation_strings": ["KAIST ,", "Sony AI ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "KAIST ,", "institution_ids": ["https://openalex.org/I157485424"]}, {"raw_affiliation_string": "Sony AI ,", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5015645563", "display_name": "Junghyun Koo", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Koo, Junghyun", "raw_affiliation_strings": ["Sony AI ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony AI ,", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5017282176", "display_name": "Marco A. Mart\u00ednez-Ram\u00edrez", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mart\u00ednez-Ram\u00edrez, Marco A.", "raw_affiliation_strings": ["Sony AI ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony AI ,", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Choi, Woosung", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Choi, Woosung", "raw_affiliation_strings": ["Sony AI ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony AI ,", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Liao, Wei-Hsiang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liao, Wei-Hsiang", "raw_affiliation_strings": ["Sony AI ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony AI ,", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024471982", "display_name": "Qiyu Wu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wu, Qiyu", "raw_affiliation_strings": ["Sony Group Corporation"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony Group Corporation", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Nam, Juhan", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I157485424", "display_name": "Korea Advanced Institute of Science and Technology", "ror": "https://ror.org/05apxxy63", "country_code": "KR", "type": "education", "lineage": ["https://openalex.org/I157485424"]}], "countries": ["KR"], "is_corresponding": false, "raw_author_name": "Nam, Juhan", "raw_affiliation_strings": ["KAIST ,"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "KAIST ,", "institution_ids": ["https://openalex.org/I157485424"]}]}, {"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": ["Sony AI ,", "Sony Group Corporation"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Sony AI ,", "institution_ids": []}, {"raw_affiliation_string": "Sony Group Corporation", "institution_ids": []}]}], "abstract_inverted_index": {"This": [0], "paper": [1], "introduces": [2], "LLM2Fx-Tools,": [3], "a": [4, 21, 49, 98, 109], "multimodal": [5], "tool-calling": [6], "framework": [7], "that": [8, 66, 121], "generates": [9, 124], "executable": [10], "sequences": [11], "of": [12, 77], "audio": [13, 28, 31, 61, 103, 148], "effects": [14, 32, 62, 104, 149], "(Fx-chain)": [15], "for": [16, 60, 130], "music": [17, 131, 155], "post-production.": [18], "LLM2Fx-Tools": [19, 67], "uses": [20], "large": [22], "language": [23], "model": [24], "(LLM)": [25], "to": [26, 114, 142, 147], "understand": [27], "inputs,": [29], "select": [30], "types,": [33], "determine": [34], "their": [35], "order,": [36], "and": [37, 57, 72, 79, 89, 112, 128, 153], "estimate": [38], "parameters,": [39], "guided": [40], "by": [41, 83], "chain-of-thought": [42], "(CoT)": [43], "planning.": [44], "We": [45, 92], "also": [46], "present": [47], "LP-Fx,": [48], "new": [50, 115], "instruction-following": [51], "dataset": [52], "with": [53], "structured": [54], "CoT": [55, 90, 126], "annotations": [56], "tool": [58, 87, 145], "calls": [59], "modules.": [63], "Experiments": [64], "show": [65], "can": [68], "infer": [69], "an": [70], "Fx-chain": [71], "its": [73], "parameters": [74], "from": [75, 108], "pairs": [76], "unprocessed": [78], "processed": [80], "audio,": [81], "enabled": [82], "autoregressive": [84], "sequence": [85], "modeling,": [86], "calling,": [88], "reasoning.": [91], "further": [93], "validate": [94], "the": [95, 139], "system": [96], "in": [97], "style": [99], "transfer": [100], "setting,": [101], "where": [102], "information": [105], "is": [106, 138], "transferred": [107], "reference": [110], "source": [111], "applied": [113], "content.": [116], "Finally,": [117], "LLM-as-a-judge": [118], "evaluation": [119], "demonstrates": [120], "our": [122, 135], "approach": [123], "appropriate": [125], "reasoning": [127], "responses": [129], "production": [132], "queries.": [133], "To": [134], "knowledge,": [136], "this": [137], "first": [140], "work": [141], "apply": [143], "LLM-based": [144], "calling": [146], "modules,": [150], "enabling": [151], "interpretable": [152], "controllable": [154], "production.": [156]}, "primary_topic": {"id": "https://openalex.org/T11309", "display_name": "Music and Audio Processing", "score": 0.8389000296592712, "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": 0.8389000296592712, "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": 0.15860000252723694, "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/T10201", "display_name": "Speech Recognition and Synthesis", "score": 0.000699999975040555, "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:2512.01559", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.01559", "pdf_url": "https://arxiv.org/pdf/2512.01559", "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/W7117114420", "doi": "https://doi.org/10.48550/arxiv.2512.19081", "title": "Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning", "publication_year": 2025, "publication_date": "2025-12-22", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5121167444", "display_name": "Yanzhi Zhang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yanzhi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067992353", "display_name": "Yitong Duan", "orcid": "https://orcid.org/0000-0002-1150-3995", "observed_orcids": ["https://orcid.org/0000-0002-1150-3995"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Duan, Yitong", "raw_affiliation_strings": ["Zhongguancun Academy", "Zhongguancun Institute of Artificial Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhongguancun Academy", "institution_ids": []}, {"raw_affiliation_string": "Zhongguancun Institute of Artificial Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5032216635", "display_name": "Zhaoxi Zhang", "orcid": "https://orcid.org/0000-0002-3813-2776", "observed_orcids": ["https://orcid.org/0000-0002-3813-2776", "https://orcid.org/0009-0005-4719-7116"]}, "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": "Zhang, Zhaoxi", "raw_affiliation_strings": ["Peking University", "Zhongguancun Institute of Artificial Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Peking University", "institution_ids": ["https://openalex.org/I20231570"]}, {"raw_affiliation_string": "Zhongguancun Institute of Artificial Intelligence", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5048009884", "display_name": "Jiyan He", "orcid": "https://orcid.org/0009-0003-4539-1826", "observed_orcids": ["https://orcid.org/0009-0003-4539-1826"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "He, Jiyan", "raw_affiliation_strings": ["Zhongguancun Academy", "Zhongguancun Institute of Artificial Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhongguancun Academy", "institution_ids": []}, {"raw_affiliation_string": "Zhongguancun Institute of Artificial Intelligence", "institution_ids": []}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5051093347", "display_name": "Shuxin Zheng", "orcid": "https://orcid.org/0000-0001-7828-5374", "observed_orcids": ["https://orcid.org/0000-0001-7828-5374"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zheng, Shuxin", "raw_affiliation_strings": ["Zhongguancun Academy", "Zhongguancun Institute of Artificial Intelligence"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Zhongguancun Academy", "institution_ids": []}, {"raw_affiliation_string": "Zhongguancun Institute of Artificial Intelligence", "institution_ids": []}]}], "abstract_inverted_index": {"Test-time": [0], "scaling": [1, 86], "has": [2], "emerged": [3], "as": [4], "a": [5, 27, 41, 79], "promising": [6], "direction": [7], "for": [8, 47], "enhancing": [9], "the": [10, 58, 68, 89, 112, 119], "reasoning": [11, 120], "capabilities": [12], "of": [13, 44, 91, 114, 122], "Large": [14], "Language": [15], "Models": [16], "in": [17, 63], "last": [18], "few": [19], "years.": [20], "In": [21], "this": [22], "work,": [23], "we": [24, 77], "propose": [25], "Population-Evolve,": [26], "training-free": [28], "method": [29], "inspired": [30], "by": [31], "Genetic": [32], "Algorithms": [33], "to": [34, 117], "optimize": [35], "LLM": [36, 59], "reasoning.": [37, 52], "Our": [38, 109], "approach": [39], "maintains": [40], "dynamic": [42], "population": [43, 62], "candidate": [45], "solutions": [46], "each": [48], "problem": [49], "via": [50, 73], "parallel": [51], "By": [53], "incorporating": [54], "an": [55], "evolve": [56], "prompt,": [57], "self-evolves": [60], "its": [61], "all": [64], "iterations.": [65], "Upon": [66], "convergence,": [67], "final": [69], "answer": [70], "is": [71], "derived": [72], "majority": [74], "voting.": [75], "Furthermore,": [76], "establish": [78], "unification": [80], "framework": [81], "that": [82, 97], "interprets": [83], "existing": [84], "test-time": [85], "strategies": [87, 116], "through": [88], "lens": [90], "genetic": [92], "algorithms.": [93], "Empirical": [94], "results": [95], "demonstrate": [96], "Population-Evolve": [98], "achieves": [99], "superior": [100], "accuracy": [101], "with": [102], "low": [103], "performance": [104], "variance": [105], "and": [106], "computational": [107], "efficiency.": [108], "findings": [110], "highlight": [111], "potential": [113], "evolutionary": [115], "unlock": [118], "power": [121], "LLMs": [123], "during": [124], "inference.": [125]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5029000043869019, "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": 0.5029000043869019, "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": 0.1964000016450882, "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": 0.06809999793767929, "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:2512.19081", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.19081", "pdf_url": "https://arxiv.org/pdf/2512.19081", "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/W4415164191", "doi": "https://doi.org/10.48550/arxiv.2506.18959", "title": "From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents", "publication_year": 2025, "publication_date": "2025-06-23", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5043782446", "display_name": "Weizhi Zhang", "orcid": "https://orcid.org/0000-0002-9131-3234", "observed_orcids": ["https://orcid.org/0000-0002-9131-3234"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Weizhi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061585074", "display_name": "Yangning Li", "orcid": "https://orcid.org/0000-0002-1991-6698", "observed_orcids": ["https://orcid.org/0000-0002-1991-6698"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Yangning", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5035660751", "display_name": "Yuanchen Bei", "orcid": "https://orcid.org/0000-0003-2834-2873", "observed_orcids": ["https://orcid.org/0000-0003-2834-2873"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bei, Yuanchen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101912906", "display_name": "Junyu Luo", "orcid": "https://orcid.org/0009-0001-6894-1144", "observed_orcids": ["https://orcid.org/0009-0001-6894-1144"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Junyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102638295", "display_name": "Guancheng Wan", "orcid": "https://orcid.org/0000-0002-7083-6423", "observed_orcids": ["https://orcid.org/0000-0002-7083-6423"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wan, Guancheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5001633360", "display_name": "Liangwei Yang", "orcid": "https://orcid.org/0000-0001-5660-766X", "observed_orcids": ["https://orcid.org/0000-0001-5660-766X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Liangwei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5034301485", "display_name": "Chenxuan Xie", "orcid": "https://orcid.org/0000-0002-4474-615X", "observed_orcids": ["https://orcid.org/0000-0002-4474-615X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xie, Chenxuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Yang, Yuyao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Yuyao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5015519124", "display_name": "Wei\u2010Chieh Huang", "orcid": "https://orcid.org/0000-0003-3759-0131", "observed_orcids": ["https://orcid.org/0000-0003-3759-0131"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Huang, Wei-Chieh", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Miao, Chunyu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Miao, Chunyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109737659", "display_name": "Henry Peng Zou", "orcid": "https://orcid.org/0009-0003-5259-4998", "observed_orcids": ["https://orcid.org/0009-0003-5259-4998"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zou, Henry Peng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101947952", "display_name": "Xiao Luo", "orcid": "https://orcid.org/0000-0001-7822-8281", "observed_orcids": ["https://orcid.org/0000-0001-7822-8281"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Luo, Xiao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101487505", "display_name": "Yusheng Zhao", "orcid": "https://orcid.org/0000-0002-8914-7951", "observed_orcids": ["https://orcid.org/0000-0002-8914-7951"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhao, Yusheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5053712210", "display_name": "Yankai Chen", "orcid": "https://orcid.org/0000-0001-5741-2047", "observed_orcids": ["https://orcid.org/0000-0001-5741-2047"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Yankai", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5018499468", "display_name": "Chunkit Chan", "orcid": "https://orcid.org/0000-0002-1520-4597", "observed_orcids": ["https://orcid.org/0000-0002-1520-4597"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chan, Chunkit", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"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": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhou, Peilin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5022999126", "display_name": "Xinyang Zhang", "orcid": "https://orcid.org/0000-0001-6474-682X", "observed_orcids": ["https://orcid.org/0000-0001-6474-682X", "https://orcid.org/0009-0006-0802-261X", "https://orcid.org/0009-0009-1751-3498"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Xinyang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5011355966", "display_name": "Chenwei Zhang", "orcid": "https://orcid.org/0000-0002-0606-3649", "observed_orcids": ["https://orcid.org/0000-0002-0606-3649"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Chenwei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5039500313", "display_name": "Jingbo Shang", "orcid": "https://orcid.org/0000-0002-7249-4404", "observed_orcids": ["https://orcid.org/0000-0002-7249-4404"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shang, Jingbo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zhang, Ming", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ming", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5020880385", "display_name": "Yangqiu Song", "orcid": "https://orcid.org/0000-0002-7818-6090", "observed_orcids": ["https://orcid.org/0000-0002-7818-6090"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Song, Yangqiu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042251906", "display_name": "Irwin King", "orcid": "https://orcid.org/0000-0001-8106-6447", "observed_orcids": ["https://orcid.org/0000-0001-8106-6447"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "King, Irwin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5036357902", "display_name": "Philip S. Yu", "orcid": "https://orcid.org/0000-0002-3491-5968", "observed_orcids": ["https://orcid.org/0000-0002-3491-5968"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yu, Philip S.", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Information": [0], "retrieval": [1], "is": [2, 34, 136], "a": [3, 49, 74, 98], "cornerstone": [4], "of": [5, 11, 106, 120], "modern": [6], "knowledge": [7], "acquisition,": [8], "enabling": [9], "billions": [10], "queries": [12], "each": [13], "day": [14], "across": [15], "diverse": [16], "domains.": [17], "However,": [18], "traditional": [19], "keyword-based": [20], "search": [21, 61, 85], "engines": [22], "are": [23, 46, 162], "increasingly": [24], "inadequate": [25], "for": [26, 144, 164], "handling": [27], "complex,": [28], "multi-step": [29], "information": [30, 60, 71, 146], "needs.": [31], "Our": [32], "position": [33], "that": [35, 90, 125], "Large": [36], "Language": [37], "Models": [38], "(LLMs),": [39], "endowed": [40], "with": [41], "reasoning": [42, 110], "and": [43, 70, 93, 111, 117, 159], "agentic": [44], "capabilities,": [45], "ushering": [47], "in": [48, 167], "new": [50], "paradigm": [51, 143], "termed": [52], "Agentic": [53, 126], "Deep": [54, 127], "Research.": [55], "These": [56], "systems": [57, 89], "transcend": [58], "conventional": [59], "techniques": [62], "by": [63, 114], "tightly": [64], "integrating": [65], "autonomous": [66], "reasoning,": [67], "iterative": [68], "retrieval,": [69], "synthesis": [72], "into": [73], "dynamic": [75], "feedback": [76], "loop.": [77], "We": [78, 95], "trace": [79], "the": [80, 104, 118, 141, 149, 165], "evolution": [81], "from": [82], "static": [83], "web": [84], "to": [86, 102, 139], "interactive,": [87], "agent-based": [88], "plan,": [91], "explore,": [92], "learn.": [94], "also": [96, 137], "introduce": [97], "test-time": [99], "scaling": [100], "law": [101], "formalize": [103], "impact": [105], "computational": [107], "depth": [108], "on": [109], "search.": [112], "Supported": [113], "benchmark": [115, 157], "results": [116], "rise": [119], "open-source": [121, 160], "implementations,": [122, 161], "we": [123], "demonstrate": [124], "Research": [128], "not": [129], "only": [130], "significantly": [131], "outperforms": [132], "existing": [133], "approaches,": [134], "but": [135], "poised": [138], "become": [140], "dominant": [142], "future": [145], "seeking.": [147], "All": [148], "related": [150], "resources,": [151], "including": [152], "industry": [153], "products,": [154], "research": [155], "papers,": [156], "datasets,": [158], "collected": [163], "community": [166], "https://github.com/DavidZWZ/Awesome-Deep-Research.": [168]}, "primary_topic": {"id": "https://openalex.org/T10286", "display_name": "Information Retrieval and Search Behavior", "score": 0.9980000257492065, "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": 0.9980000257492065, "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": 0.0010999999940395355, "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"}}, {"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "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:2506.18959", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.18959", "pdf_url": "https://arxiv.org/pdf/2506.18959", "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/W4414969291", "doi": "https://doi.org/10.48550/arxiv.2510.03574", "title": "Efficient Test-Time Scaling for Small Vision-Language Models", "publication_year": 2025, "publication_date": "2025-10-03", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Kaya, Mehmet Onurcan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kaya, Mehmet Onurcan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5010165733", "display_name": "Desmond Elliott", "orcid": "https://orcid.org/0000-0003-3112-7904", "observed_orcids": ["https://orcid.org/0000-0003-3112-7904"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Elliott, Desmond", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5073141800", "display_name": "Dim P. Papadopoulos", "orcid": "https://orcid.org/0000-0002-5278-2273", "observed_orcids": ["https://orcid.org/0000-0002-5278-2273"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Papadopoulos, Dim P.", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Small": [0], "Vision-Language": [1], "Models": [2], "(VLMs)": [3], "provide": [4], "a": [5], "computationally": [6, 37], "efficient": [7, 56], "alternative": [8], "to": [9], "larger": [10], "models,": [11], "at": [12, 81, 133], "the": [13, 40, 62, 82], "cost": [14], "of": [15, 44, 125], "weaker": [16], "generalization": [17], "abilities": [18], "and": [19, 55, 78, 88, 136], "downstream": [20], "task": [21], "performance.": [22], "These": [23], "shortcomings": [24], "could": [25], "be": [26], "addressed": [27], "by": [28], "test-time": [29, 57], "scaling": [30, 58], "techniques,": [31], "but": [32], "existing": [33], "methods": [34], "are": [35], "typically": [36], "demanding,": [38], "contradicting": [39], "resource-efficient": [41], "design": [42], "goals": [43], "small": [45], "models.": [46], "To": [47], "address": [48], "these": [49], "limitations,": [50], "we": [51, 110], "propose": [52], "two": [53], "novel": [54], "strategies": [59], "that": [60], "leverage": [61], "model-internal": [63], "features": [64], "rather": [65], "than": [66], "external": [67], "supervision:": [68], "(i)": [69], "Test-Time": [70, 90], "Augmentation": [71], "(TTAug),": [72], "which": [73, 93], "generates": [74], "multiple": [75], "augmented": [76], "inputs": [77], "aggregates": [79], "outputs": [80], "token": [83], "level": [84], "without": [85, 140], "parameter": [86], "updates,": [87], "(ii)": [89], "Adaptation": [91], "(TTAdapt),": [92], "adapts": [94], "model": [95], "parameters": [96], "during": [97], "inference": [98], "using": [99], "consensus-based": [100], "pseudolabels": [101], "from": [102], "TTAug.": [103], "Through": [104], "extensive": [105], "experiments": [106], "across": [107, 137], "nine": [108], "benchmarks,": [109], "demonstrate": [111], "consistent": [112], "performance": [113], "improvements": [114], "while": [115], "maintaining": [116], "computational": [117], "efficiency": [118], "suitable": [119], "for": [120], "resource-constrained": [121], "environments.": [122], "The": [123], "generality": [124], "our": [126], "approach": [127], "is": [128], "demonstrated": [129], "both": [130], "within": [131], "models": [132], "different": [134, 138], "scales": [135], "VLMs": [139], "additional": [141], "tuning.": [142]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9897000193595886, "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": 0.9897000193595886, "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": 0.004600000102072954, "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": 0.004100000020116568, "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:2510.03574", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.03574", "pdf_url": "https://arxiv.org/pdf/2510.03574", "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/W4414581665", "doi": "https://doi.org/10.48550/arxiv.2505.18759", "title": "The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation", "publication_year": 2025, "publication_date": "2025-05-24", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "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": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ruichen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065198798", "display_name": "Rana Muhammad Shahroz Khan", "orcid": "https://orcid.org/0009-0003-7103-0573", "observed_orcids": ["https://orcid.org/0009-0003-7103-0573"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Khan, Rana Muhammad Shahroz", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103086062", "display_name": "Zhen Tan", "orcid": "https://orcid.org/0000-0002-1061-0393", "observed_orcids": ["https://orcid.org/0000-0002-1061-0393"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tan, Zhen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100324961", "display_name": "Dawei Li", "orcid": "https://orcid.org/0000-0002-9048-5229", "observed_orcids": ["https://orcid.org/0000-0002-9048-5229", "https://orcid.org/0000-0001-9049-8516"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Dawei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5037347051", "display_name": "Song Wang", "orcid": "https://orcid.org/0000-0002-8758-7988", "observed_orcids": ["https://orcid.org/0000-0002-8758-7988"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Song", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5103073431", "display_name": "Tianlong Chen", "orcid": "https://orcid.org/0000-0001-7774-8197", "observed_orcids": ["https://orcid.org/0000-0001-7774-8197"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Tianlong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Data-centric": [0], "distillation,": [1], "including": [2], "data": [3, 53, 63, 87], "augmentation,": [4], "selection,": [5], "and": [6, 62, 73, 103, 107, 117, 135], "mixing,": [7], "offers": [8], "a": [9, 31, 98], "promising": [10], "path": [11], "to": [12, 34, 113], "creating": [13], "smaller,": [14], "more": [15, 133], "efficient": [16], "student": [17, 74, 90], "Large": [18], "Language": [19], "Models": [20], "(LLMs)": [21], "that": [22, 51], "retain": [23], "strong": [24], "reasoning": [25, 95, 137], "abilities.": [26], "However,": [27], "there": [28], "still": [29], "lacks": [30], "comprehensive": [32], "benchmark": [33, 50], "systematically": [35], "assess": [36], "the": [37, 47, 83, 130], "effect": [38], "of": [39, 85, 132], "each": [40], "distillation": [41, 58, 124], "approach.": [42], "This": [43], "paper": [44], "introduces": [45], "DC-CoT,": [46], "first": [48], "data-centric": [49, 126], "investigates": [52], "manipulation": [54], "in": [55], "chain-of-thought": [56], "(CoT)": [57], "from": [59], "method,": [60], "model": [61, 91], "perspectives.": [64], "Utilizing": [65], "various": [66], "teacher": [67], "models": [68], "(e.g.,": [69, 76], "o4-mini,": [70], "Gemini-Pro,": [71], "Claude-3.5)": [72], "architectures": [75], "3B,": [77], "7B": [78], "parameters),": [79], "we": [80], "rigorously": [81], "evaluate": [82], "impact": [84], "these": [86], "manipulations": [88], "on": [89, 100], "performance": [92], "across": [93], "multiple": [94], "datasets,": [96], "with": [97], "focus": [99], "in-distribution": [101], "(IID)": [102], "out-of-distribution": [104], "(OOD)": [105], "generalization,": [106], "cross-domain": [108], "transfer.": [109], "Our": [110], "findings": [111], "aim": [112], "provide": [114], "actionable": [115], "insights": [116], "establish": [118], "best": [119], "practices": [120], "for": [121], "optimizing": [122], "CoT": [123], "through": [125], "techniques,": [127], "ultimately": [128], "facilitating": [129], "development": [131], "accessible": [134], "capable": [136], "models.": [138], "The": [139], "codebase": [140], "can": [141], "be": [142], "accessed": [143], "at": [144], "https://github.com/UNITES-Lab/Distillation-Bench": [145]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8270999789237976, "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": 0.8270999789237976, "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": 0.11029999703168869, "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": 0.016200000420212746, "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:2505.18759", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.18759", "pdf_url": "https://arxiv.org/pdf/2505.18759", "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/W4414944822", "doi": "https://doi.org/10.48550/arxiv.2507.11102", "title": "KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model", "publication_year": 2025, "publication_date": "2025-07-15", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yang, Jie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yang, Jie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zeng, Wang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zeng, Wang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103846971", "display_name": "Sheng Jin", "orcid": "https://orcid.org/0000-0003-4737-9516", "observed_orcids": ["https://orcid.org/0000-0003-4737-9516"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Jin, Sheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5032828647", "display_name": "Lumin Xu", "orcid": "https://orcid.org/0000-0003-2125-2760", "observed_orcids": ["https://orcid.org/0000-0003-2125-2760"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xu, Lumin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5038428177", "display_name": "Wentao Liu", "orcid": "https://orcid.org/0000-0001-7599-4650", "observed_orcids": ["https://orcid.org/0000-0001-7599-4650"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Wentao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5015264548", "display_name": "Qian Chen", "orcid": "https://orcid.org/0009-0006-2281-0719", "observed_orcids": ["https://orcid.org/0009-0006-2281-0719"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qian, Chen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100332568", "display_name": "Zhen Li", "orcid": "https://orcid.org/0000-0002-0001-2998", "observed_orcids": ["https://orcid.org/0000-0002-0001-2998", "https://orcid.org/0000-0001-7947-3887"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Zhen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5003608795", "display_name": "Ruimao Zhang", "orcid": "https://orcid.org/0000-0001-9511-7532", "observed_orcids": ["https://orcid.org/0000-0001-9511-7532"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Ruimao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"The": [0, 115], "emergence": [1], "of": [2, 35, 45, 88, 145], "Multimodal": [3], "Large": [4], "Language": [5], "Models": [6], "(MLLMs)": [7], "has": [8], "revolutionized": [9], "image": [10, 59, 163, 204], "understanding": [11, 205], "by": [12, 93], "bridging": [13], "textual": [14], "and": [15, 33, 42, 63, 129, 165, 182, 206], "visual": [16], "modalities.": [17], "However,": [18], "these": [19], "models": [20], "often": [21], "struggle": [22], "with": [23, 167], "capturing": [24], "fine-grained": [25, 58, 203], "semantic": [26], "information,": [27], "such": [28, 56], "as": [29, 39, 57, 106, 198], "the": [30, 86, 143, 151], "precise": [31, 133], "identification": [32], "analysis": [34], "object": [36, 61], "keypoints.": [37], "Keypoints,": [38], "structure-aware,": [40], "pixel-level,": [41], "compact": [43], "representations": [44], "objects,": [46, 160], "particularly": [47], "articulated": [48], "ones,": [49], "play": [50], "a": [51, 72, 120, 136, 199], "crucial": [52], "role": [53], "in": [54], "applications": [55], "analysis,": [60], "retrieval,": [62], "behavior": [64], "recognition.": [65], "In": [66], "this": [67], "paper,": [68], "we": [69, 147], "propose": [70], "KptLLM++,": [71], "novel": [73, 121], "multimodal": [74], "large": [75], "language": [76], "model": [77, 116], "that": [78], "specifically": [79], "designed": [80], "for": [81, 202, 210], "generic": [82], "keypoint": [83, 98, 127, 161, 188], "comprehension": [84], "through": [85, 135], "integration": [87], "diverse": [89, 159], "input": [90], "modalities": [91], "guided": [92], "user-defined": [94], "instructions.": [95], "By": [96], "unifying": [97], "detection": [99, 189], "across": [100], "varied": [101], "contexts,": [102], "KptLLM++": [103, 174], "establishes": [104], "itself": [105], "an": [107], "advanced": [108], "interface,": [109], "fostering": [110], "more": [111], "effective": [112], "human-AI": [113, 211], "collaboration.": [114], "is": [117], "built": [118], "upon": [119], "identify-then-detect": [122], "paradigm,": [123], "which": [124], "first": [125], "interprets": [126], "semantics": [128], "subsequently": [130], "localizes": [131], "their": [132], "positions": [134], "structured": [137], "chain-of-thought": [138], "reasoning": [139], "mechanism.": [140], "To": [141], "push": [142], "boundaries": [144], "performance,": [146, 194], "have": [148], "scaled": [149], "up": [150], "training": [152], "dataset": [153], "to": [154, 175], "over": [155], "500K": [156], "samples,": [157], "encompassing": [158], "categories,": [162], "styles,": [164], "scenarios": [166], "complex": [168], "occlusions.": [169], "This": [170], "extensive": [171], "scaling": [172], "enables": [173], "unlock": [176], "its": [177, 192, 196, 207], "potential,": [178], "achieving": [179], "remarkable": [180], "accuracy": [181], "generalization.": [183], "Comprehensive": [184], "experiments": [185], "on": [186], "multiple": [187], "benchmarks": [190], "demonstrate": [191], "state-of-the-art": [193], "underscoring": [195], "potential": [197], "unified": [200], "solution": [201], "transformative": [208], "implications": [209], "interaction.": [212]}, "primary_topic": {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.9351000189781189, "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": 0.9351000189781189, "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": 0.03700000047683716, "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/T10812", "display_name": "Human Pose and Action Recognition", "score": 0.010400000028312206, "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:2507.11102", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2507.11102", "pdf_url": "https://arxiv.org/pdf/2507.11102", "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/W4414633044", "doi": "https://doi.org/10.48550/arxiv.2504.15777", "title": "Tina: Tiny Reasoning Models via LoRA", "publication_year": 2025, "publication_date": "2025-04-22", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102785891", "display_name": "Shangshang Wang", "orcid": "https://orcid.org/0009-0005-0996-5380", "observed_orcids": ["https://orcid.org/0009-0005-0996-5380"]}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Wang, Shangshang", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5092950123", "display_name": "Julian Asilis", "orcid": "https://orcid.org/0000-0002-7047-3861", "observed_orcids": ["https://orcid.org/0000-0002-7047-3861"]}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Asilis, Julian", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5028059095", "display_name": "\u00d6mer Faruk Akg\u00fcl", "orcid": "https://orcid.org/0000-0003-1588-3670", "observed_orcids": ["https://orcid.org/0000-0003-1588-3670"]}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Akg\u00fcl, \u00d6mer Faruk", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109467016", "display_name": "Emrullah Bilgin", "orcid": null, "observed_orcids": []}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Bilgin, Enes Burak", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5041927922", "display_name": "Ollie Liu", "orcid": null, "observed_orcids": []}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Liu, Ollie", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5073310637", "display_name": "Willie Neiswanger", "orcid": "https://orcid.org/0000-0002-9619-5572", "observed_orcids": ["https://orcid.org/0000-0002-9619-5572"]}, "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"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Neiswanger, Willie", "raw_affiliation_strings": ["University of Southern California"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "University of Southern California", "institution_ids": ["https://openalex.org/I1174212"]}]}], "abstract_inverted_index": {"How": [0], "cost-effectively": [1], "can": [2, 36], "strong": [3], "reasoning": [4, 23, 34, 70, 81, 116, 148, 157, 191], "abilities": [5], "be": [6, 37], "achieved": [7, 25, 92], "in": [8], "language": [9], "models?": [10], "Driven": [11], "by": [12, 43, 103, 193], "this": [13, 90, 153, 175], "fundamental": [14], "question,": [15], "we": [16, 172, 210], "present": [17], "Tina,": [18], "a": [19, 94, 114, 165], "family": [20], "of": [21, 97, 145, 169, 190, 205], "tiny": [22, 58, 95], "models": [24, 67, 82], "with": [26, 164], "high": [27], "cost-efficiency.": [28], "Notably,": [29], "Tina": [30, 111], "demonstrates": [31], "that": [32, 68, 174], "substantial": [33], "performance": [35, 71, 117], "developed": [38], "using": [39, 51], "only": [40, 126], "minimal": [41], "resources,": [42], "applying": [44], "parameter-efficient": [45], "updates": [46], "during": [47], "reinforcement": [48], "learning": [49], "(RL),": [50], "low-rank": [52], "adaptation": [53], "(LoRA),": [54], "to": [55, 186], "an": [56, 134], "already": [57], "1.5B": [59], "parameter": [60], "base": [61, 87, 199], "model.": [62, 88], "This": [63], "minimalist": [64], "approach": [65], "produces": [66], "achieve": [69], "which": [72], "is": [73, 91], "competitive": [74], "with,": [75], "and": [76, 119, 130, 159, 177, 207, 217], "sometimes": [77], "surpasses,": [78], "SOTA": [79, 105], "RL": [80, 147], "built": [83], "upon": [84], "the": [85, 98, 109, 142, 184, 187, 198], "same": [86], "Crucially,": [89], "at": [93, 125], "fraction": [96], "computational": [99], "post-training": [100, 129], "cost": [101, 132, 137], "employed": [102], "existing": [104], "models.": [106], "In": [107, 203], "fact,": [108], "best": [110], "model": [112, 185, 218], "achieves": [113], ">20\\%": [115], "increase": [118], "43.33\\%": [120], "Pass@1": [121], "accuracy": [122], "on": [123], "AIME24,": [124], "\\$9": [127], "USD": [128], "evaluation": [131], "(i.e.,": [133], "estimated": [135], "260x": [136], "reduction).": [138], "Our": [139], "work": [140], "reveals": [141], "surprising": [143], "effectiveness": [144, 176], "efficient": [146], "via": [149], "LoRA.": [150], "We": [151], "validate": [152], "across": [154], "multiple": [155], "open-source": [156, 212], "datasets": [158], "various": [160], "ablation": [161], "settings": [162], "starting": [163], "single,": [166], "fixed": [167], "set": [168], "hyperparameters.": [170], "Furthermore,": [171], "hypothesize": [173], "efficiency": [178], "stem": [179], "from": [180], "LoRA": [181], "rapidly": [182], "adapting": [183], "structural": [188], "format": [189], "rewarded": [192], "RL,": [194], "while": [195], "largely": [196], "preserving": [197], "model's": [200], "underlying": [201], "knowledge.": [202], "service": [204], "accessibility": [206], "open": [208], "research,": [209], "fully": [211], "all": [213], "code,": [214], "training": [215], "logs,": [216], "weights": [219], "\\&": [220], "checkpoints.": [221]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.6240000128746033, "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": 0.6240000128746033, "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": 0.1656000018119812, "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": 0.06669999659061432, "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:2504.15777", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.15777", "pdf_url": "https://arxiv.org/pdf/2504.15777", "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/W4412549363", "doi": "https://doi.org/10.51846/jcsa.v2i1.4278", "title": "Semantically-Aligned Reasoning for Safe AGI via Knowledge-Based Deep Models", "publication_year": 2025, "publication_date": "2025-06-01", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Noor ul Ain Zaidi", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I142732210", "display_name": "University of Engineering and Technology Lahore", "ror": "https://ror.org/0051w2v06", "country_code": "PK", "type": "education", "lineage": ["https://openalex.org/I142732210"]}], "countries": ["PK"], "is_corresponding": false, "raw_author_name": "Noor ul Ain Zaidi", "raw_affiliation_strings": ["Department of Computer Science, University of Engineering and Technology (UET), Lahore, Pakistan"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science, University of Engineering and Technology (UET), Lahore, Pakistan", "institution_ids": ["https://openalex.org/I142732210"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5108869433", "display_name": "Sundas Fatima", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I142204992", "display_name": "University of Lahore", "ror": "https://ror.org/051jrjw38", "country_code": "PK", "type": "education", "lineage": ["https://openalex.org/I142204992"]}, {"id": "https://openalex.org/I142732210", "display_name": "University of Engineering and Technology Lahore", "ror": "https://ror.org/0051w2v06", "country_code": "PK", "type": "education", "lineage": ["https://openalex.org/I142732210"]}], "countries": ["PK"], "is_corresponding": false, "raw_author_name": "Sundas Fatima", "raw_affiliation_strings": ["Department of Computer Science and Information Technology, The University of Lahore, Lahore Campus, Pakistan"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Computer Science and Information Technology, The University of Lahore, Lahore Campus, Pakistan", "institution_ids": ["https://openalex.org/I142204992", "https://openalex.org/I142732210"]}]}], "abstract_inverted_index": {"A": [0, 112], "hybrid": [1], "neuro-symbolic": [2], "framework": [3, 64], "is": [4], "presented": [5], "in": [6, 21, 30], "this": [7], "work": [8], "with": [9, 53, 74, 84], "the": [10, 14, 31, 68, 75, 137], "goal": [11], "of": [12, 19, 33, 71, 78], "enhancing": [13], "safety,": [15], "dependability,": [16], "and": [17, 50, 59, 90, 99, 107, 125, 133], "interpretability": [18], "reasoning": [20, 88], "large": [22], "language": [23, 57], "models": [24], "(LLMs),": [25], "which": [26], "will": [27], "ultimately": [28], "aid": [29], "development": [32], "reliable": [34], "artificial": [35], "general": [36], "intelligence": [37], "(AGI).The": [38], "proposed": [39], "strategy": [40], "integrates": [41], "structured": [42], "knowledge": [43], "representations,": [44], "such": [45], "as": [46, 128, 130], "ontologies,": [47], "symbolic": [48, 72], "planners,": [49], "formal": [51], "logic,": [52], "deep": [54], "learning-based": [55], "natural": [56], "comprehension": [58], "Chain-of-Thought": [60], "(CoT)": [61], "reasoning.": [62], "The": [63], "aims": [65], "to": [66, 80, 119], "combine": [67], "semantic": [69, 82], "rigor": [70], "systems": [73], "generative": [76], "flexibility": [77], "LLMs": [79], "ensure": [81], "alignment": [83, 108], "human": [85], "ideals,": [86], "improve": [87], "faithfulness,": [89], "lessen": [91], "hallucinations.": [92], "Adversarial": [93], "robustness": [94], "testing,": [95], "logic-based": [96], "inference": [97], "validation,": [98], "a": [100], "benchmark": [101], "suite": [102], "for": [103], "assessing": [104], "coherence,": [105], "honesty,": [106], "are": [109, 135], "important": [110], "elements.": [111], "functioning": [113], "prototype": [114], "that": [115], "may": [116], "be": [117], "applied": [118], "high-stakes": [120], "decision-making": [121], "domains,": [122], "including": [123], "healthcare": [124], "autonomous": [126], "systems,": [127], "well": [129], "assessment": [131], "metrics": [132], "tools,": [134], "among": [136], "anticipated": [138], "results.": [139]}, "primary_topic": {"id": "https://openalex.org/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.6650000214576721, "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/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.6650000214576721, "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": 0.07859999686479568, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.04699999839067459, "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:10.51846/jcsa.v2i1.4278", "is_oa": true, "landing_page_url": "https://doi.org/10.51846/jcsa.v2i1.4278", "pdf_url": null, "source": {"id": "https://openalex.org/S5407023187", "display_name": "Journal of Computational Science and Applications (JCSA)", "issn_l": "2710-3102", "issn": ["2710-3102", "3079-0867"], "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": "Journal of Computational Science and Applications (JCSA), ISSN: 3079-0867 (Onilne)", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4414586801", "doi": "https://doi.org/10.48550/arxiv.2505.19640", "title": "Interleaved Reasoning for Large Language Models via Reinforcement Learning", "publication_year": 2025, "publication_date": "2025-05-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5104269642", "display_name": "Roy Xie", "orcid": "https://orcid.org/0009-0001-1096-1820", "observed_orcids": ["https://orcid.org/0009-0001-1096-1820"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Xie, Roy", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079902855", "display_name": "David Qiu", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Qiu, David", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102955499", "display_name": "Deepak Gopinath", "orcid": "https://orcid.org/0000-0002-5597-4860", "observed_orcids": ["https://orcid.org/0000-0002-5597-4860"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Gopinath, Deepak", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5082953595", "display_name": "Lin Jian Dong", "orcid": "https://orcid.org/0000-0003-0236-8784", "observed_orcids": ["https://orcid.org/0000-0003-0236-8784"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Lin, Dong", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067750782", "display_name": "Yanchao Sun", "orcid": "https://orcid.org/0000-0001-7392-4472", "observed_orcids": ["https://orcid.org/0000-0001-7392-4472"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Sun, Yanchao", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115591208", "display_name": "Chong Wang", "orcid": "https://orcid.org/0009-0007-4414-5147", "observed_orcids": ["https://orcid.org/0009-0007-4414-5147"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Wang, Chong", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044514249", "display_name": "Saloni Potdar", "orcid": "https://orcid.org/0009-0006-0607-6104", "observed_orcids": ["https://orcid.org/0009-0006-0607-6104"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Potdar, Saloni", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5055033421", "display_name": "Bhuwan Dhingra", "orcid": "https://orcid.org/0000-0002-6874-9515", "observed_orcids": ["https://orcid.org/0000-0002-6874-9515"]}, "institutions": [{"id": "https://openalex.org/I170897317", "display_name": "Duke University", "ror": "https://ror.org/00py81415", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I170897317"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Dhingra, Bhuwan", "raw_affiliation_strings": ["Duke University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Duke University", "institution_ids": ["https://openalex.org/I170897317"]}]}], "abstract_inverted_index": {"Long": [0], "chain-of-thought": [1], "(CoT)": [2], "significantly": [3], "enhances": [4], "the": [5, 53, 80], "reasoning": [6, 15, 37, 85, 150, 171, 178], "capabilities": [7], "of": [8], "large": [9], "language": [10], "models": [11, 50], "(LLMs).": [12], "However,": [13], "extensive": [14], "traces": [16], "lead": [17], "to": [18, 35, 39, 55, 74, 176, 191], "inefficiencies": [19], "and": [20, 42, 101, 107, 126, 154, 169, 184], "increased": [21], "time-to-first-token": [22], "(TTFT).": [23], "We": [24, 47, 66], "propose": [25], "a": [26, 68, 141], "training": [27], "paradigm": [28], "that": [29, 49], "uses": [30], "only": [31], "reinforcement": [32], "learning": [33], "(RL)": [34], "guide": [36], "LLMs": [38], "interleave": [40], "thinking": [41], "answering": [43, 168], "for": [44], "multi-hop": [45], "questions.": [46], "observe": [48], "inherently": [51], "possess": [52], "ability": [54], "perform": [56], "interleaved": [57, 93], "reasoning,": [58, 115], "which": [59], "can": [60], "be": [61], "further": [62], "enhanced": [63], "through": [64], "RL.": [65, 136], "introduce": [67], "simple": [69], "yet": [70], "effective": [71, 132], "reward": [72, 198], "scheme": [73], "incentivize": [75], "correct": [76, 84], "intermediate": [77, 89], "steps,": [78], "guiding": [79], "policy": [81], "model": [82], "toward": [83], "paths": [86], "by": [87, 129, 152, 156], "leveraging": [88], "signals": [90], "generated": [91], "during": [92, 135], "reasoning.": [94], "Extensive": [95], "experiments": [96], "across": [97], "five": [98], "diverse": [99], "datasets": [100, 179], "three": [102], "RL": [103], "algorithms": [104], "(PPO,": [105], "GRPO,": [106], "REINFORCE++)": [108], "demonstrate": [109], "consistent": [110], "improvements": [111], "over": [112, 157], "traditional": [113], "think-answer": [114], "without": [116], "requiring": [117], "external": [118], "tools.": [119], "Our": [120], "method": [121], "improves": [122], "final": [123], "task": [124], "accuracy": [125], "overall": [127, 149], "efficiency": [128], "enabling": [130], "more": [131], "credit": [133], "assignment": [134], "Specifically,": [137], "our": [138, 162], "approach": [139], "achieves": [140], "12.5%": [142], "improvement": [143], "in": [144], "Pass@1": [145], "accuracy,": [146], "while": [147], "reducing": [148], "length": [151], "37%": [153], "TTFT": [155], "80%": [158], "on": [159, 166], "average.": [160], "Furthermore,": [161], "method,": [163], "trained": [164], "solely": [165], "question": [167], "logical": [170], "datasets,": [172], "exhibits": [173], "strong": [174], "generalization": [175], "complex": [177], "such": [180], "as": [181], "MATH,": [182], "GPQA,": [183], "MMLU.": [185], "Additionally,": [186], "we": [187], "conduct": [188], "in-depth": [189], "analysis": [190], "reveal": [192], "several": [193], "valuable": [194], "insights": [195], "into": [196], "conditional": [197], "modeling.": [199]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8140000104904175, "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": 0.8140000104904175, "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": 0.07680000364780426, "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": 0.031300000846385956, "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:2505.19640", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.19640", "pdf_url": "https://arxiv.org/pdf/2505.19640", "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/W4409643903", "doi": "https://doi.org/10.21203/rs.3.rs-6275325/v1", "title": "GPTVD: Vulnerability Detection and Analysis Method Based on LLM's Chain of Thoughts.", "publication_year": 2025, "publication_date": "2025-04-21", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5037288936", "display_name": "Yinan Chen", "orcid": "https://orcid.org/0000-0003-0858-2087", "observed_orcids": ["https://orcid.org/0000-0003-0858-2087"]}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yinan Chen", "raw_affiliation_strings": ["School of Software Engineering, Sun Yat-sen University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Software Engineering, Sun Yat-sen University", "institution_ids": ["https://openalex.org/I157773358"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101812436", "display_name": "Yuan Huang", "orcid": "https://orcid.org/0000-0002-9548-0208", "observed_orcids": ["https://orcid.org/0000-0002-9548-0208", "https://orcid.org/0009-0006-1691-0959"]}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yuan Huang", "raw_affiliation_strings": ["School of Software Engineering, Sun Yat-sen University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Software Engineering, Sun Yat-sen University", "institution_ids": ["https://openalex.org/I157773358"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101601497", "display_name": "Xiangping Chen", "orcid": "https://orcid.org/0000-0001-8234-3186", "observed_orcids": ["https://orcid.org/0000-0001-8234-3186"]}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiangping Chen", "raw_affiliation_strings": ["School of Journalism and Communication, Sun Yat-sen University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Journalism and Communication, Sun Yat-sen University", "institution_ids": ["https://openalex.org/I157773358"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5060129857", "display_name": "Pengfei Shen", "orcid": "https://orcid.org/0000-0003-3048-8847", "observed_orcids": ["https://orcid.org/0000-0003-3048-8847"]}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Pengfei Shen", "raw_affiliation_strings": ["School of Software Engineering, Sun Yat-sen University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Software Engineering, Sun Yat-sen University", "institution_ids": ["https://openalex.org/I157773358"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Lei Yun", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I157773358", "display_name": "Sun Yat-sen University", "ror": "https://ror.org/0064kty71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I157773358"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Lei Yun", "raw_affiliation_strings": ["School of Software Engineering, Sun Yat-sen University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Software Engineering, Sun Yat-sen University", "institution_ids": ["https://openalex.org/I157773358"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T10260", "display_name": "Software Engineering Research", "score": 0.5776000022888184, "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": 0.5776000022888184, "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/T12479", "display_name": "Web Application Security Vulnerabilities", "score": 0.17270000278949738, "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/T10743", "display_name": "Software Testing and Debugging Techniques", "score": 0.14990000426769257, "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": "doi:10.21203/rs.3.rs-6275325/v1", "is_oa": true, "landing_page_url": "https://doi.org/10.21203/rs.3.rs-6275325/v1", "pdf_url": "https://www.researchsquare.com/article/rs-6275325/latest.pdf", "source": {"id": "https://openalex.org/S4306525896", "display_name": "Research Square", "issn_l": null, "issn": null, "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", "license_id": "https://openalex.org/licenses/cc-by", "version": "acceptedVersion", "is_accepted": true, "is_published": false, "raw_source_name": "Research Square", "raw_type": "posted-content"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4407091402", "doi": "https://doi.org/10.48550/arxiv.2501.19180", "title": "Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning", "publication_year": 2025, "publication_date": "2025-01-31", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Yang, Xianglin", "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"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Yang, Xianglin", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5029243457", "display_name": "Gelei Deng", "orcid": "https://orcid.org/0000-0002-0046-6674", "observed_orcids": ["https://orcid.org/0000-0002-0046-6674"]}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Deng, Gelei", "raw_affiliation_strings": ["Nanyang Technological University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nanyang Technological University", "institution_ids": ["https://openalex.org/I172675005"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5007796732", "display_name": "J. Y. Shi", "orcid": "https://orcid.org/0000-0002-0465-1551", "observed_orcids": ["https://orcid.org/0000-0002-0465-1551", "https://orcid.org/0009-0000-6832-523X"]}, "institutions": [{"id": "https://openalex.org/I14243506", "display_name": "Hong Kong Polytechnic University", "ror": "https://ror.org/0030zas98", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I14243506"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Shi, Jieming", "raw_affiliation_strings": ["The Hong Kong Polytechnic University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Hong Kong Polytechnic University", "institution_ids": ["https://openalex.org/I14243506"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101591101", "display_name": "Tianwei Zhang", "orcid": "https://orcid.org/0000-0001-6595-6650", "observed_orcids": ["https://orcid.org/0000-0001-6595-6650"]}, "institutions": [{"id": "https://openalex.org/I172675005", "display_name": "Nanyang Technological University", "ror": "https://ror.org/02e7b5302", "country_code": "SG", "type": "education", "lineage": ["https://openalex.org/I172675005"]}], "countries": ["SG"], "is_corresponding": false, "raw_author_name": "Zhang, Tianwei", "raw_affiliation_strings": ["Nanyang Technological University"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Nanyang Technological University", "institution_ids": ["https://openalex.org/I172675005"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5085067496", "display_name": "Jin Song Dong", "orcid": "https://orcid.org/0000-0002-6512-8326", "observed_orcids": ["https://orcid.org/0000-0002-6512-8326"]}, "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": "Dong, Jin Song", "raw_affiliation_strings": ["National University of Singapore"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "National University of Singapore", "institution_ids": ["https://openalex.org/I165932596"]}]}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2], "(LLMs)": [3], "are": [4], "vital": [5], "for": [6, 69], "a": [7, 54], "wide": [8], "range": [9], "of": [10, 24, 67, 72, 105], "applications": [11], "yet": [12], "remain": [13], "susceptible": [14], "to": [15, 21, 37, 48, 86, 140], "jailbreak": [16], "threats,": [17], "which": [18, 61], "could": [19], "lead": [20], "the": [22, 63, 89, 103, 116, 126], "generation": [23], "inappropriate": [25], "responses.": [26], "Conventional": [27], "defenses,": [28, 137], "such": [29], "as": [30], "refusal": [31, 83], "and": [32, 111, 143], "adversarial": [33, 144], "training,": [34], "often": [35], "fail": [36], "cover": [38], "corner": [39], "cases": [40], "or": [41], "rare": [42], "domains,": [43], "leaving": [44], "LLMs": [45, 68, 106], "still": [46], "vulnerable": [47], "more": [49], "sophisticated": [50], "attacks.": [51], "We": [52], "propose": [53], "novel": [55], "defense": [56], "strategy,": [57], "Safety": [58], "Chain-of-Thought": [59], "(SCoT),": [60], "harnesses": [62], "enhanced": [64], "\\textit{reasoning": [65], "capabilities}": [66], "proactive": [70, 99], "assessment": [71], "harmful": [73, 109], "inputs,": [74], "rather": [75], "than": [76], "simply": [77], "blocking": [78], "them.": [79], "SCoT": [80, 101, 133], "augments": [81], "any": [82], "training": [84], "datasets": [85], "critically": [87], "analyze": [88], "intent": [90], "behind": [91], "each": [92], "request": [93], "before": [94], "generating": [95], "answers.": [96], "By": [97], "employing": [98], "reasoning,": [100], "enhances": [102], "generalization": [104], "across": [107], "varied": [108], "queries": [110], "scenarios": [112], "not": [113], "covered": [114], "in": [115], "safety": [117], "alignment": [118], "corpus.": [119], "Additionally,": [120], "it": [121], "generates": [122], "detailed": [123], "refusals": [124], "specifying": [125], "rules": [127], "violated.": [128], "Comparative": [129], "evaluations": [130], "show": [131], "that": [132], "significantly": [134], "surpasses": [135], "existing": [136], "reducing": [138], "vulnerability": [139], "out-of-distribution": [141], "issues": [142], "manipulations": [145], "while": [146], "maintaining": [147], "strong": [148], "general": [149], "capabilities.": [150]}, "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/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"}}, {"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:2501.19180", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2501.19180", "pdf_url": "https://arxiv.org/pdf/2501.19180", "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/W4407786696", "doi": "https://doi.org/10.48550/arxiv.2502.13942", "title": "A Chain-of-Thought Subspace Meta-Learning for Few-shot Image Captioning with Large Vision and Language Models", "publication_year": 2025, "publication_date": "2025-02-19", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5084563249", "display_name": "Hao Huang", "orcid": "https://orcid.org/0000-0003-3151-367X", "observed_orcids": ["https://orcid.org/0000-0003-3151-367X", "https://orcid.org/0000-0003-0170-1290"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Huang, Hao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5041372265", "display_name": "Shuaihang Yuan", "orcid": "https://orcid.org/0000-0002-7092-7966", "observed_orcids": ["https://orcid.org/0000-0002-7092-7966"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yuan, Shuaihang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102925195", "display_name": "Hao Yu", "orcid": "https://orcid.org/0000-0002-5662-5910", "observed_orcids": ["https://orcid.org/0000-0002-5662-5910"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hao, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062799681", "display_name": "Congcong Wen", "orcid": "https://orcid.org/0000-0001-6448-003X", "observed_orcids": ["https://orcid.org/0000-0001-6448-003X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wen, Congcong", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5083935587", "display_name": "Yi Fang", "orcid": "https://orcid.org/0000-0001-9427-3883", "observed_orcids": ["https://orcid.org/0000-0001-9427-3883"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fang, Yi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"A": [0], "large-scale": [1], "vision": [2, 46, 89], "and": [3, 15, 25, 31, 47, 90, 201], "language": [4, 26, 91, 128], "model": [5, 175], "that": [6, 27, 212], "has": [7, 77], "been": [8, 78], "pretrained": [9, 87], "on": [10, 191], "massive": [11], "data": [12, 52, 62], "encodes": [13], "visual": [14, 120], "linguistic": [16], "prior,": [17], "which": [18, 130], "makes": [19], "it": [20], "easier": [21], "to": [22, 69, 80, 117, 125, 132, 157, 169, 177, 184, 220], "generate": [23, 133], "images": [24, 124], "are": [28, 63], "more": [29], "natural": [30], "realistic.": [32], "Despite": [33], "this,": [34], "there": [35], "is": [36, 53, 218], "still": [37], "a": [38, 73, 95, 113, 139, 146, 152], "significant": [39], "domain": [40], "gap": [41, 83], "between": [42, 84], "the": [43, 82, 107, 119, 127, 174, 221], "modalities": [44], "of": [45, 122, 173, 208, 225], "language,": [48], "especially": [49], "when": [50], "training": [51, 141], "scarce": [54], "in": [55, 181, 223], "few-shot": [56, 104, 204], "settings,": [57], "where": [58], "only": [59, 138], "very": [60], "limited": [61], "available": [64], "for": [65], "training.": [66], "In": [67, 164], "order": [68], "mitigate": [70], "this": [71], "issue,": [72], "multi-modal": [74], "meta-learning": [75, 110, 149, 216], "framework": [76, 111], "proposed": [79], "bridge": [81], "two": [85, 100], "frozen": [86], "large": [88, 101], "models": [92], "by": [93, 231], "introducing": [94], "tunable": [96], "prompt": [97], "connecting": [98], "these": [99], "models.": [102], "For": [103], "image": [105, 135, 154, 195], "captioning,": [106], "existing": [108], "multi-model": [109], "utilizes": [112], "one-step": [114], "prompting": [115], "scheme": [116, 150], "accumulate": [118], "features": [121], "input": [123], "guide": [126], "model,": [129], "struggles": [131], "accurate": [134], "descriptions": [136], "with": [137], "few": [140], "samples.": [142], "Instead,": [143], "we": [144, 166], "propose": [145, 168], "chain-of-thought": [147, 214], "(CoT)": [148], "as": [151], "multi-step": [153], "captioning": [155, 196], "procedure": [156], "better": [158], "imitate": [159], "how": [160], "humans": [161], "describe": [162], "images.": [163], "addition,": [165], "further": [167], "learn": [170], "different": [171, 228, 232], "meta-parameters": [172], "corresponding": [176], "each": [178], "CoT": [179], "step": [180], "distinct": [182], "subspaces": [183], "avoid": [185], "interference.": [186], "We": [187], "evaluated": [188], "our": [189, 209, 213], "method": [190], "three": [192], "commonly": [193], "used": [194], "datasets,": [197], "i.e.,": [198], "MSCOCO,": [199], "Flickr8k,": [200], "Flickr30k,": [202], "under": [203], "settings.": [205], "The": [206], "results": [207], "experiments": [210], "indicate": [211], "subspace": [215], "strategy": [217], "superior": [219], "baselines": [222], "terms": [224], "performance": [226], "across": [227], "datasets": [229], "measured": [230], "metrics.": [233]}, "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/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"}}, {"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": "pmh:oai:arXiv.org:2502.13942", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2502.13942", "pdf_url": "https://arxiv.org/pdf/2502.13942", "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/W4416050177", "doi": "https://doi.org/10.22214/ijraset.2025.75054", "title": "Prompt Engineering for Controlling LLM Behavior: A Practical Framework and Case Study Evaluation", "publication_year": 2025, "publication_date": "2025-11-09", "type": "article", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Princy Hareshbhai Patel", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I70764227", "display_name": "Indus University", "ror": "https://ror.org/03ehk1n67", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I70764227"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Princy Hareshbhai Patel", "raw_affiliation_strings": ["IITE , Indus University , Ahmedabad"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "IITE , Indus University , Ahmedabad", "institution_ids": ["https://openalex.org/I70764227"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5120318225", "display_name": "Sanjana Suthar", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I70764227", "display_name": "Indus University", "ror": "https://ror.org/03ehk1n67", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I70764227"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Sanjana Suthar", "raw_affiliation_strings": ["IITE , Indus University , Ahmedabad"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "IITE , Indus University , Ahmedabad", "institution_ids": ["https://openalex.org/I70764227"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5021538493", "display_name": "Hiren V. Mer", "orcid": "https://orcid.org/0000-0002-8452-3794", "observed_orcids": ["https://orcid.org/0000-0002-8452-3794"]}, "institutions": [{"id": "https://openalex.org/I70764227", "display_name": "Indus University", "ror": "https://ror.org/03ehk1n67", "country_code": "IN", "type": "education", "lineage": ["https://openalex.org/I70764227"]}], "countries": ["IN"], "is_corresponding": false, "raw_author_name": "Prof. Hiren Mer", "raw_affiliation_strings": ["IITE , Indus University , Ahmedabad"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "IITE , Indus University , Ahmedabad", "institution_ids": ["https://openalex.org/I70764227"]}]}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "are": [4], "highly": [5], "sensitive": [6], "to": [7], "prompt": [8, 22], "design.": [9], "We": [10, 26], "present": [11], "the": [12, 28, 72, 76], "Prompt": [13], "Effectiveness": [14], "Evaluator": [15], "(PEE),": [16], "a": [17, 37, 51], "modular": [18], "toolkit": [19], "for": [20, 93], "comparing": [21], "variants": [23], "across": [24], "tasks.": [25], "detail": [27], "architecture,": [29], "metrics": [30], "(ROUGE-L,": [31], "BLEU,": [32], "BERTScore,": [33], "sentiment),": [34], "and": [35, 50, 63, 69], "contribute": [36], "new": [38], "applied": [39], "case": [40], "study": [41], "on": [42], "sales": [43, 47], "projection.": [44], "Using": [45], "monthly": [46], "data": [48], "(Jan\u2013Sep)": [49], "reference": [52], "projection": [53], "(Oct\u2013Dec),": [54], "we": [55], "evaluate": [56], "three": [57], "prompts\u2014Zero-shot": [58], "concise,": [59], "Role": [60, 66], "+": [61, 67], "constraints,": [62], "Chain-of-Thought": [64], "(CoT).": [65], "constraints": [68], "Zero-shot": [70], "achieve": [71], "strongest": [73], "overlap": [74], "with": [75], "numeric": [77], "reference;": [78], "CoT": [79], "is": [80], "close": [81], "but": [82], "slightly": [83], "lower.": [84], "Results": [85], "show": [86], "that": [87], "PEE": [88], "provides": [89], "reproducible,": [90], "metrics-driven": [91], "guidance": [92], "selecting": [94], "effective": [95], "prompts.": [96]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.951200008392334, "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": 0.951200008392334, "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": 0.03269999846816063, "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/T13904", "display_name": "Artificial Intelligence Applications", "score": 0.003700000001117587, "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:10.22214/ijraset.2025.75054", "is_oa": true, "landing_page_url": "https://doi.org/10.22214/ijraset.2025.75054", "pdf_url": "https://doi.org/10.22214/ijraset.2025.75054", "source": {"id": "https://openalex.org/S2764566388", "display_name": "International Journal for Research in Applied Science and Engineering Technology", "issn_l": "2321-9653", "issn": ["2321-9653"], "is_oa": true, "is_in_doaj": false, "is_core": false, "listed_in": [], "host_organization": "https://openalex.org/P4322614460", "host_organization_name": "International Journal for Research in Applied Science and Engineering Technology (IJRASET)", "host_organization_lineage": ["https://openalex.org/P4322614460"], "host_organization_lineage_names": ["International Journal for Research in Applied Science and Engineering Technology (IJRASET)"], "type": "journal"}, "license": null, "license_id": null, "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "International Journal for Research in Applied Science and Engineering Technology", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4410939926", "doi": "https://doi.org/10.31234/osf.io/86xsj_v24", "title": "WITHDRAWN", "publication_year": 2025, "publication_date": "2025-06-02", "type": "preprint", "language": "en", "authorships": [], "abstract_inverted_index": {"Given": [0], "its": [1], "ubiquity": [2], "in": [3, 11, 21, 30, 48], "mental": [4], "life,": [5], "the": [6, 23, 59, 71, 97, 101, 114, 134, 156, 198], "precise": [7], "role": [8, 47], "of": [9, 26, 162, 200], "language": [10, 183], "enabling": [12, 118], "complex": [13], "thought": [14], "and": [15, 54, 86, 108, 125, 155, 181], "reasoning": [16, 29, 160], "remains": [17], "difficult": [18], "to": [19, 104, 113, 120, 136], "study": [20], "humans.However,": [22], "surprising": [24], "emergence": [25], "sophisticated": [27], "symbolic": [28, 89, 94, 110, 142, 179], "purely": [31], "connectionist": [32, 176], "Large": [33], "Language": [34], "Models": [35], "(LLMs)-systems": [36], "learning": [37, 177], "only": [38], "from": [39, 70, 145], "text-provides": [40], "a": [41, 56, 80, 139, 172, 190], "novel": [42], "empirical": [43], "lens": [44], "on": [45], "language's": [46], "cognition,": [49], "challenging": [50], "historical": [51], "symbolic-connectionist": [52], "dichotomies": [53], "compelling": [55], "re-evaluation.We": [57], "introduce": [58], "Emergent": [60], "Symbolic": [61], "Cognition": [62], "(ESC)": [63], "framework,": [64], "proposing": [65], "that": [66, 92], "general": [67, 201], "intelligence": [68], "arises": [69], "dynamic": [72], "interaction": [73], "between": [74], "an": [75, 87, 185], "adaptive": [76], "continuous": [77], "substrate": [78, 102, 135], "(like": [79], "brain": [81], "or": [82, 205], "Artificial": [83], "Neural": [84], "Network)": [85], "internalized": [88], "framework.ESC": [90], "posits": [91], "recursive": [93], "generation": [95], "is": [96], "core": [98], "computational": [99], "engine:": [100], "learns": [103], "sequentially": [105], "generate,": [106], "process,": [107], "evaluate": [109], "sequences": [111], "according": [112], "framework's": [115], "implicit": [116], "rules,": [117], "it": [119], "navigate": [121], "vast": [122], "combinatorial": [123], "spaces": [124], "construct": [126], "structured": [127], "solutions": [128], "for": [129, 193], "diverse": [130], "problems.This": [131], "process": [132], "allows": [133], "operate": [137], "as": [138, 184], "powerful,": [140], "discrete": [141], "processor.Converging": [143], "evidence": [144], "human": [146], "cognitive": [147, 187], "development,": [148], "inner": [149], "speech,": [150], "neuroscience": [151], "(aphasia,": [152], "DMN": [153], "activity),": [154], "striking,": [157], "though": [158], "nascent,": [159], "abilities": [161], "LLMs": [163], "(e.g.,": [164], "chain-of-thought,": [165], "crossdomain": [166], "transfer)": [167], "supports": [168], "ESC.This": [169], "framework": [170], "offers": [171], "unifying": [173], "perspective,": [174], "reconciling": [175], "with": [178], "competence": [180], "reframing": [182], "inherited": [186], "engine,": [188], "establishing": [189], "conceptual": [191], "scaffold": [192], "future": [194], "interdisciplinary": [195], "inquiry": [196], "into": [197], "foundations": [199], "intelligence,": [202], "whether": [203], "biological": [204], "artificial.": [206]}, "primary_topic": {"id": "https://openalex.org/T14394", "display_name": "Cognitive Science and Education Research", "score": 0.2741999924182892, "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"}}, "topics": [{"id": "https://openalex.org/T14394", "display_name": "Cognitive Science and Education Research", "score": 0.2741999924182892, "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/T10258", "display_name": "Philosophy and Theoretical Science", "score": 0.14489999413490295, "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": 0.09040000289678574, "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:10.31234/osf.io/86xsj_v24", "is_oa": true, "landing_page_url": "https://doi.org/10.31234/osf.io/86xsj_v24", "pdf_url": "https://osf.io/86xsj_v24/download", "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/W7104916054", "doi": "https://doi.org/10.48550/arxiv.2511.06739", "title": "Rank-1 LoRAs Encode Interpretable Reasoning Signals", "publication_year": 2025, "publication_date": "2025-11-10", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Ward, Jake", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ward, Jake", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Riechers, Paul", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Riechers, Paul", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Shai, Adam", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shai, Adam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Reasoning": [0], "models": [1, 12, 39, 57], "leverage": [2], "inference-time": [3], "compute": [4], "to": [5, 65, 82, 97, 153], "significantly": [6], "enhance": [7], "the": [8, 30, 33, 50, 105, 128], "performance": [9, 35, 95, 146], "of": [10, 36, 52, 71, 93, 107, 132], "language": [11, 184], "on": [13, 127], "difficult": [14], "logical": [15], "tasks,": [16], "and": [17, 116, 135, 138, 157, 187], "have": [18], "become": [19], "a": [20, 79, 84, 98, 124, 176], "dominating": [21], "paradigm": [22], "in": [23, 55], "frontier": [24], "LLMs.": [25], "Despite": [26], "their": [27], "wide": [28], "adoption,": [29], "mechanisms": [31], "underpinning": [32], "enhanced": [34], "these": [37, 72, 160], "reasoning": [38, 56, 145], "are": [40, 110], "not": [41], "well": [42], "understood.": [43], "In": [44], "this": [45, 108, 133], "work,": [46], "we": [47, 77, 122], "show": [48], "that": [49, 104, 144, 168], "majority": [51], "new": [53], "capabilities": [54], "can": [58, 147, 172], "be": [59, 173], "elicited": [60], "by": [61], "small,": [62], "single-rank": [63], "changes": [64, 73, 152, 161], "base": [66, 154], "model": [67, 155, 185], "parameters,": [68, 156], "with": [69], "many": [70], "being": [74], "interpretable.": [75], "Specifically,": [76], "use": [78], "rank-1": [80], "LoRA": [81, 109, 134], "create": [83], "minimal": [85, 151], "parameter": [86, 100], "adapter": [87], "for": [88, 118, 179], "Qwen-2.5-32B-Instruct": [89], "which": [90], "recovers": [91], "73-90%": [92], "reasoning-benchmark": [94], "compared": [96], "full": [99], "finetune.": [101], "We": [102], "find": [103], "activations": [106], "as": [111, 113, 175], "interpretable": [112], "MLP": [114], "neurons,": [115], "fire": [117], "reasoning-specific": [119], "behaviors.": [120], "Finally,": [121], "train": [123], "sparse": [125], "autoencoder": [126], "entire": [129], "activation": [130], "state": [131], "identify": [136], "fine-grained": [137], "monosemantic": [139], "features.": [140], "Our": [141], "findings": [142], "highlight": [143], "arise": [148], "largely": [149], "from": [150], "explore": [158], "what": [159], "affect.": [162], "More": [163], "broadly,": [164], "our": [165], "work": [166], "shows": [167], "parameter-efficient": [169], "training": [170], "methods": [171], "used": [174], "targeted": [177], "lens": [178], "uncovering": [180], "fundamental": [181], "insights": [182], "about": [183], "behavior": [186], "dynamics.": [188]}, "primary_topic": {"id": "https://openalex.org/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.6093999743461609, "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/T12026", "display_name": "Explainable Artificial Intelligence (XAI)", "score": 0.6093999743461609, "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": 0.2628999948501587, "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": 0.057999998331069946, "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:2511.06739", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.06739", "pdf_url": "https://arxiv.org/pdf/2511.06739", "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/W7106680102", "doi": "https://doi.org/10.48550/arxiv.2511.17923", "title": "Towards Efficient LLM-aware Heterogeneous Graph Learning", "publication_year": 2025, "publication_date": "2025-11-22", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Li, Wenda", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Li, Wenda", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Zheng, Tongya", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zheng, Tongya", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Liu, Shunyu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Shunyu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Wang, Yu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Yu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Chen, Kaixuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Kaixuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Yuan, Hanyang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yuan, Hanyang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Hu, Bingde", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hu, Bingde", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Ren, Zujie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ren, Zujie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Song, Mingli", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Song, Mingli", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Chen, Gang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Gang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Heterogeneous": [0], "graphs": [1, 31, 85, 99, 191], "are": [2, 32], "widely": [3], "present": [4], "in": [5, 29, 83, 91, 107, 200], "real-world": [6], "complex": [7, 19, 26, 126], "networks,": [8], "where": [9], "the": [10, 35, 42, 76, 121, 158, 179, 201], "diversity": [11], "of": [12, 37, 44, 79, 160], "node": [13], "and": [14, 20, 41, 50, 81, 174, 203, 213], "relation": [15, 27, 127, 162], "types": [16], "leads": [17], "to": [18, 56, 74, 138, 166, 210, 216], "rich": [21, 58], "semantics.": [22], "Efforts": [23], "for": [24, 117], "modeling": [25], "semantics": [28], "heterogeneous": [30, 84, 98, 118, 190], "restricted": [33], "by": [34, 103], "limitations": [36], "predefined": [38], "semantic": [39, 63, 77, 170], "dependencies": [40], "scarcity": [43], "supervised": [45], "signals.": [46], "The": [47], "advanced": [48], "pre-training": [49, 173], "fine-tuning": [51, 175], "paradigm": [52], "leverages": [53, 136], "graph": [54], "structure": [55], "provide": [57], "self-supervised": [59], "signals,": [60], "but": [61, 94], "introduces": [62], "gaps": [64, 171], "between": [65, 172], "tasks.": [66], "Large": [67], "Language": [68], "Models": [69], "(LLMs)": [70], "offer": [71], "significant": [72], "potential": [73], "address": [75], "issues": [78], "relations": [80], "tasks": [82], "through": [86], "their": [87, 95], "strong": [88], "reasoning": [89, 163], "capabilities": [90], "textual": [92, 182], "modality,": [93], "incorporation": [96], "into": [97], "is": [100, 227], "largely": [101], "limited": [102], "computational": [104, 145], "complexity.": [105], "Therefore,": [106], "this": [108], "paper,": [109], "we": [110, 129, 147, 177], "propose": [111, 130], "an": [112, 131], "Efficient": [113], "LLM-Aware": [114], "(ELLA)": [115], "framework": [116], "graphs,": [119], "addressing": [120], "above": [122], "issues.": [123], "To": [124, 143, 168], "capture": [125], "semantics,": [128], "LLM-aware": [132, 161], "Relation": [133, 152], "Tokenizer": [134], "that": [135, 193], "LLM": [137], "encode": [139], "multi-hop,": [140], "multi-type": [141], "relations.": [142], "reduce": [144], "complexity,": [146], "further": [148], "employ": [149], "a": [150, 217], "Hop-level": [151], "Graph": [153], "Transformer,": [154], "which": [155], "help": [156], "reduces": [157], "complexity": [159], "from": [164], "exponential": [165], "linear.": [167], "bridge": [169], "tasks,": [176], "introduce": [178], "fine-grained": [180], "task-aware": [181], "Chain-of-Thought": [183], "(CoT)": [184], "prompts.": [185], "Extensive": [186], "experiments": [187], "on": [188], "four": [189], "show": [192], "our": [194], "proposed": [195], "ELLA": [196, 207], "outperforms": [197], "state-of-the-art": [198], "methods": [199], "performance": [202], "efficiency.": [204], "In": [205], "particular,": [206], "scales": [208], "up": [209, 215], "13b-parameter": [211], "LLMs": [212], "achieves": [214], "4x": [218], "speedup": [219], "compared": [220], "with": [221], "existing": [222], "LLM-based": [223], "methods.": [224], "Our": [225], "code": [226], "publicly": [228], "available": [229], "at": [230], "https://github.com/l-wd/ELLA.": [231]}, "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/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:2511.17923", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.17923", "pdf_url": "https://arxiv.org/pdf/2511.17923", "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/W4406152280", "doi": "https://doi.org/10.1038/s41591-024-03416-6", "title": "A generalist medical language model for disease diagnosis assistance", "publication_year": 2025, "publication_date": "2025-01-08", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5051416661", "display_name": "Xiaohong Liu", "orcid": "https://orcid.org/0000-0003-4931-8370", "observed_orcids": ["https://orcid.org/0000-0003-4931-8370", "https://orcid.org/0000-0001-8326-2038", "https://orcid.org/0000-0003-0377-8398"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiaohong Liu", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Hao Liu", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hao Liu", "raw_affiliation_strings": ["Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5062546203", "display_name": "Guoxing Yang", "orcid": "https://orcid.org/0009-0009-1056-2430", "observed_orcids": ["https://orcid.org/0009-0009-1056-2430"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Guoxing Yang", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": "https://orcid.org/0009-0009-1056-2430", "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Zeyu Jiang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zeyu Jiang", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5009164482", "display_name": "Shuguang Robert Cui", "orcid": "https://orcid.org/0000-0003-2608-775X", "observed_orcids": ["https://orcid.org/0000-0003-2608-775X"]}, "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"]}, {"id": "https://openalex.org/I4210116924", "display_name": "Chinese University of Hong Kong, Shenzhen", "ror": "https://ror.org/02d5ks197", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I177725633", "https://openalex.org/I180726961", "https://openalex.org/I4210116924"]}], "countries": ["CN", "HK"], "is_corresponding": false, "raw_author_name": "Shuguang Cui", "raw_affiliation_strings": ["School of Science and Engineering (SSE), Future Network of Intelligence Institute (FNii) and Guangdong Provincial Key Laboratory of Future Networks of Intelligence, Chinese University of Hong Kong, Shenzhen, China"], "raw_orcid": "https://orcid.org/0000-0003-2608-775X", "affiliations": [{"raw_affiliation_string": "School of Science and Engineering (SSE), Future Network of Intelligence Institute (FNii) and Guangdong Provincial Key Laboratory of Future Networks of Intelligence, Chinese University of Hong Kong, Shenzhen, China", "institution_ids": ["https://openalex.org/I177725633", "https://openalex.org/I4210116924"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5014379853", "display_name": "Zhaoze Zhang", "orcid": "https://orcid.org/0009-0006-0711-9508", "observed_orcids": ["https://orcid.org/0009-0006-0711-9508"]}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhaoze Zhang", "raw_affiliation_strings": ["Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China"], "raw_orcid": "https://orcid.org/0009-0006-0711-9508", "affiliations": [{"raw_affiliation_string": "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101977048", "display_name": "Huan Wang", "orcid": "https://orcid.org/0000-0001-7337-9005", "observed_orcids": ["https://orcid.org/0000-0001-7337-9005"]}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Huan Wang", "raw_affiliation_strings": ["Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5090283045", "display_name": "Liyuan Tao", "orcid": "https://orcid.org/0000-0003-3497-1326", "observed_orcids": ["https://orcid.org/0000-0003-3497-1326"]}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Liyuan Tao", "raw_affiliation_strings": ["Research Center of Clinical Epidemiology, Peking University Third Hospital, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Research Center of Clinical Epidemiology, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5012052127", "display_name": "Yongchang Sun", "orcid": "https://orcid.org/0000-0003-3281-8854", "observed_orcids": ["https://orcid.org/0000-0003-3281-8854"]}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Yongchang Sun", "raw_affiliation_strings": ["Department of Respiratory and Critical Care Medicine, Peking University Third Hospital and Research Center for Chronic Airway Diseases, Peking University Health Science Center, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Respiratory and Critical Care Medicine, Peking University Third Hospital and Research Center for Chronic Airway Diseases, Peking University Health Science Center, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5143820539", "display_name": "Zhu Song", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zhu Song", "raw_affiliation_strings": ["Department of Respiratory and Critical Care Medicine, Peking University Third Hospital and Research Center for Chronic Airway Diseases, Peking University Health Science Center, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Respiratory and Critical Care Medicine, Peking University Third Hospital and Research Center for Chronic Airway Diseases, Peking University Health Science Center, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5006301048", "display_name": "Tianpei Hong", "orcid": "https://orcid.org/0000-0002-5744-5129", "observed_orcids": ["https://orcid.org/0000-0002-5744-5129"]}, "institutions": [{"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tianpei Hong", "raw_affiliation_strings": ["Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0002-5744-5129", "affiliations": [{"raw_affiliation_string": "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019872937", "display_name": "Jin Yang", "orcid": "https://orcid.org/0000-0001-6004-955X", "observed_orcids": ["https://orcid.org/0000-0001-6004-955X"]}, "institutions": [{"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jin Yang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0001-6004-955X", "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019872937", "display_name": "Jin Yang", "orcid": "https://orcid.org/0000-0001-6004-955X", "observed_orcids": ["https://orcid.org/0000-0001-6004-955X"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jin Yang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0001-6004-955X", "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}, {"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5103284688", "display_name": "Tianrun Gao", "orcid": "https://orcid.org/0009-0002-6063-1034", "observed_orcids": ["https://orcid.org/0009-0002-6063-1034"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Tianrun Gao", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5143773309", "display_name": "Jiangjiang Zhang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jiangjiang Zhang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5143810078", "display_name": "Xiaohu Li", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Xiaohu Li", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}, {"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5143763767", "display_name": "Jing Zhang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jing Zhang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5086350742", "display_name": "Zhao Yang", "orcid": "https://orcid.org/0000-0002-5891-5815", "observed_orcids": ["https://orcid.org/0000-0002-5891-5815"]}, "institutions": [{"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I20231570", "display_name": "Peking University", "ror": "https://ror.org/02v51f717", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I20231570"]}, {"id": "https://openalex.org/I4210130930", "display_name": "Peking University First Hospital", "ror": "https://ror.org/02z1vqm45", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210130930"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ye Sang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "Peking University First Hospital and Research Center of Public Policy, Peking University, Beijing, China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "Peking University First Hospital and Research Center of Public Policy, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570", "https://openalex.org/I4210130930"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5143808409", "display_name": "Zhao Yang", "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"]}, {"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/I4210130930", "display_name": "Peking University First Hospital", "ror": "https://ror.org/02z1vqm45", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210130930"]}], "countries": ["CN", "GB"], "is_corresponding": false, "raw_author_name": "Zhao Yang", "raw_affiliation_strings": ["Peking University First Hospital and Research Center of Public Policy, Peking University, Beijing, China", "Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Peking University First Hospital and Research Center of Public Policy, Peking University, Beijing, China", "institution_ids": ["https://openalex.org/I20231570", "https://openalex.org/I4210130930"]}, {"raw_affiliation_string": "Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5068228244", "display_name": "Kanmin Xue", "orcid": "https://orcid.org/0000-0003-0065-9131", "observed_orcids": ["https://orcid.org/0000-0003-0065-9131"]}, "institutions": [{"id": "https://openalex.org/I180726961", "display_name": "Shenzhen University", "ror": "https://ror.org/01vy4gh70", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I180726961"]}, {"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": ["CN", "GB"], "is_corresponding": false, "raw_author_name": "Kanmin Xue", "raw_affiliation_strings": ["Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK", "South China Hospital, Medical School, Shenzhen University, Shenzhen, China"], "raw_orcid": "https://orcid.org/0000-0003-0065-9131", "affiliations": [{"raw_affiliation_string": "Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK", "institution_ids": ["https://openalex.org/I40120149"]}, {"raw_affiliation_string": "South China Hospital, Medical School, Shenzhen University, Shenzhen, China", "institution_ids": ["https://openalex.org/I180726961"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5055454866", "display_name": "Song Wu", "orcid": "https://orcid.org/0000-0003-3504-1630", "observed_orcids": ["https://orcid.org/0000-0003-3504-1630", "https://orcid.org/0000-0001-8690-127X", "https://orcid.org/0000-0001-7876-7007", "https://orcid.org/0000-0003-4485-6110"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I180726961", "display_name": "Shenzhen University", "ror": "https://ror.org/01vy4gh70", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I180726961"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Song Wu", "raw_affiliation_strings": ["South China Hospital, Medical School, Shenzhen University, Shenzhen, China", "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0003-3504-1630", "affiliations": [{"raw_affiliation_string": "South China Hospital, Medical School, Shenzhen University, Shenzhen, China", "institution_ids": ["https://openalex.org/I180726961"]}, {"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100405787", "display_name": "Ping Zhang", "orcid": "https://orcid.org/0000-0002-0269-104X", "observed_orcids": ["https://orcid.org/0000-0002-0269-104X", "https://orcid.org/0000-0001-7114-1095"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Ping Zhang", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China"], "raw_orcid": "https://orcid.org/0000-0002-0269-104X", "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}, {"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100644503", "display_name": "Jian Yang", "orcid": "https://orcid.org/0000-0002-1391-1482", "observed_orcids": ["https://orcid.org/0000-0002-1391-1482"]}, "institutions": [{"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Jian Yang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0002-1391-1482", "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}, {"raw_affiliation_string": "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100458577", "display_name": "Guangyu Wang", "orcid": "https://orcid.org/0000-0003-1312-884X", "observed_orcids": ["https://orcid.org/0000-0003-1312-884X"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I161350542", "display_name": "China Three Gorges University", "ror": "https://ror.org/0419nfc77", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I161350542"]}, {"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}, {"id": "https://openalex.org/I4210152080", "display_name": "Yichang Central People's Hospital", "ror": "https://ror.org/04cr34a11", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210152080"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jian Yang", "raw_affiliation_strings": ["Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"], "raw_orcid": "https://orcid.org/0000-0002-1391-1482", "affiliations": [{"raw_affiliation_string": "Department of Cardiology, The First College of Clinical Medical Science, China Three Gorges University and Yichang Central People's Hospital, Yichang, China. yangjian@ctgu.edu.cn", "institution_ids": ["https://openalex.org/I161350542", "https://openalex.org/I4210152080"]}, {"raw_affiliation_string": "Department of Endocrinology and Metabolism, Peking University Third Hospital, Beijing, China", "institution_ids": ["https://openalex.org/I4210141942"]}, {"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5074876487", "display_name": "Chunli Song", "orcid": "https://orcid.org/0000-0002-3690-9457", "observed_orcids": ["https://orcid.org/0000-0002-3690-9457", "https://orcid.org/0009-0008-8234-6924"]}, "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"]}, {"id": "https://openalex.org/I4210141942", "display_name": "Peking University Third Hospital", "ror": "https://ror.org/04wwqze12", "country_code": "CN", "type": "healthcare", "lineage": ["https://openalex.org/I4210141942"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Chunli Song", "raw_affiliation_strings": ["Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China. schl@bjmu.edu.cn"], "raw_orcid": "https://orcid.org/0000-0002-3690-9457", "affiliations": [{"raw_affiliation_string": "Department of Orthopedics, Peking University Third Hospital & Beijing Key Laboratory of Spinal Disease & Engineering Research Center of Bone and Joint Precision Medicine, Beijing, China. schl@bjmu.edu.cn", "institution_ids": ["https://openalex.org/I20231570", "https://openalex.org/I4210141942"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100458577", "display_name": "Guangyu Wang", "orcid": "https://orcid.org/0000-0003-1312-884X", "observed_orcids": ["https://orcid.org/0000-0003-1312-884X"]}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}, {"id": "https://openalex.org/I4392021250", "display_name": "State Key Laboratory of Networking and Switching Technology", "ror": "https://ror.org/00qtv5q45", "country_code": null, "type": "facility", "lineage": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Guangyu Wang", "raw_affiliation_strings": ["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China. guangyu.wang24@gmail.com"], "raw_orcid": "https://orcid.org/0000-0003-1312-884X", "affiliations": [{"raw_affiliation_string": "State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China. guangyu.wang24@gmail.com", "institution_ids": ["https://openalex.org/I139759216", "https://openalex.org/I4392021250"]}]}], "abstract_inverted_index": null, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.801800012588501, "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": 0.801800012588501, "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": 0.18320000171661377, "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": 0.006300000008195639, "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:10.1038/s41591-024-03416-6", "is_oa": false, "landing_page_url": "https://doi.org/10.1038/s41591-024-03416-6", "pdf_url": null, "source": {"id": "https://openalex.org/S203256638", "display_name": "Nature Medicine", "issn_l": "1078-8956", "issn": ["1078-8956", "1546-170X", "1744-7933"], "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 Medicine", "raw_type": "journal-article"}, "cited_by_count": 179, "is_retracted": false}, {"id": "https://openalex.org/W4416615452", "doi": "https://doi.org/10.48550/arxiv.2510.19842", "title": "DAG-Math: Graph-of-Thought Guided Mathematical Reasoning in LLMs", "publication_year": 2025, "publication_date": "2025-10-19", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Zhang, Yuanhe", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I39555362", "display_name": "University of Warwick", "ror": "https://ror.org/01a77tt86", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I39555362"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Zhang, Yuanhe", "raw_affiliation_strings": ["Department of Statistics , University of Warwick , United Kingdom;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Statistics , University of Warwick , United Kingdom;", "institution_ids": ["https://openalex.org/I39555362"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5041854594", "display_name": "Ilja Kuzborskij", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I4210090411", "display_name": "Google DeepMind (United Kingdom)", "ror": "https://ror.org/00971b260", "country_code": "GB", "type": "company", "lineage": ["https://openalex.org/I4210090411", "https://openalex.org/I4210128969"]}], "countries": ["GB"], "is_corresponding": false, "raw_author_name": "Kuzborskij, Ilja", "raw_affiliation_strings": ["Google DeepMind , United Kingdom;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Google DeepMind , United Kingdom;", "institution_ids": ["https://openalex.org/I4210090411"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5059740024", "display_name": "Jason D. Lee", "orcid": "https://orcid.org/0000-0003-0064-7800", "observed_orcids": ["https://orcid.org/0000-0003-0064-7800"]}, "institutions": [{"id": "https://openalex.org/I39555362", "display_name": "University of Warwick", "ror": "https://ror.org/01a77tt86", "country_code": "GB", "type": "education", "lineage": ["https://openalex.org/I39555362"]}, {"id": "https://openalex.org/I95457486", "display_name": "University of California, Berkeley", "ror": "https://ror.org/01an7q238", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I95457486"]}], "countries": ["GB", "US"], "is_corresponding": false, "raw_author_name": "Lee, Jason D.", "raw_affiliation_strings": ["Department of Electrical Engineering and Computer Sciences , also Department of Statistics , University of California , Berkeley , USA;", "ment of Computer Science , and Centre for Discrete Mathematics and its Applications (DIMAP) , University of Warwick , United Kingdom;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Electrical Engineering and Computer Sciences , also Department of Statistics , University of California , Berkeley , USA;", "institution_ids": ["https://openalex.org/I95457486"]}, {"raw_affiliation_string": "ment of Computer Science , and Centre for Discrete Mathematics and its Applications (DIMAP) , University of Warwick , United Kingdom;", "institution_ids": ["https://openalex.org/I39555362"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5042142807", "display_name": "Chenlei Leng", "orcid": "https://orcid.org/0000-0001-5703-9617", "observed_orcids": ["https://orcid.org/0000-0001-5703-9617"]}, "institutions": [{"id": "https://openalex.org/I14243506", "display_name": "Hong Kong Polytechnic University", "ror": "https://ror.org/0030zas98", "country_code": "HK", "type": "education", "lineage": ["https://openalex.org/I14243506"]}], "countries": ["HK"], "is_corresponding": false, "raw_author_name": "Leng, Chenlei", "raw_affiliation_strings": ["Department of Applied Mathematics , Hong Kong Polytechnic University , Hong Kong ;"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Applied Mathematics , Hong Kong Polytechnic University , Hong Kong ;", "institution_ids": ["https://openalex.org/I14243506"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5016703530", "display_name": "Fanghui Liu", "orcid": "https://orcid.org/0000-0003-4133-7921", "observed_orcids": ["https://orcid.org/0000-0003-4133-7921"]}, "institutions": [{"id": "https://openalex.org/I4210158445", "display_name": "Institute of Natural Science", "ror": "https://ror.org/004tze884", "country_code": "KP", "type": "education", "lineage": ["https://openalex.org/I4210158445"]}], "countries": ["KP"], "is_corresponding": false, "raw_author_name": "Liu, Fanghui", "raw_affiliation_strings": ["School of Mathematical Sciences , Institute of Natural Sciences and MOE-LSC , Shanghai Jiao Tong University , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Mathematical Sciences , Institute of Natural Sciences and MOE-LSC , Shanghai Jiao Tong University , China", "institution_ids": ["https://openalex.org/I4210158445"]}]}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "demonstrate": [4], "strong": [5], "performance": [6], "on": [7, 93], "mathematical": [8, 128], "problems": [9], "when": [10, 144], "prompted": [11], "with": [12], "Chain-of-Thought": [13], "(CoT),": [14], "yet": [15], "it": [16], "remains": [17], "unclear": [18], "whether": [19], "this": [20, 60, 113], "success": [21], "stems": [22], "from": [23], "search,": [24], "rote": [25], "procedures,": [26], "or": [27], "rule-consistent": [28, 153], "reasoning.": [29], "To": [30], "address": [31], "this,": [32, 94], "we": [33, 62, 95], "propose": [34], "modeling": [35], "CoT": [36, 74, 99, 110, 162], "as": [37], "a": [38, 66, 72, 103, 158], "certain": [39], "rule-based": [40], "stochastic": [41], "process": [42], "over": [43], "directed": [44], "acyclic": [45], "graphs": [46], "(DAGs),": [47], "where": [48], "nodes": [49], "represent": [50], "intermediate": [51], "derivation": [52], "states": [53], "and": [54, 101, 152, 163, 176], "edges": [55], "encode": [56], "rule": [57], "applications.": [58], "Within": [59], "framework,": [61], "introduce": [63, 96], "\\textbf{logical": [64], "closeness},": [65], "metric": [67], "that": [68, 105], "quantifies": [69], "how": [70], "well": [71], "model's": [73], "trajectory": [75], "(i.e.,": [76], "the": [77, 83, 97, 117], "LLM's": [78], "final": [79], "output)": [80], "adheres": [81], "to": [82, 108], "DAG": [84], "structure,": [85], "providing": [86], "evaluation": [87, 118], "beyond": [88], "classical": [89], "PASS@$k$": [90, 145], "metrics.": [91], "Building": [92], "\\emph{DAG-MATH}": [98], "format": [100], "construct": [102], "benchmark": [104, 175], "guides": [106], "LLMs": [107, 171], "generate": [109], "trajectories": [111], "in": [112, 137], "format,": [114], "thereby": [115], "enabling": [116], "of": [119], "their": [120], "reasoning": [121, 129, 138, 172], "ability": [122], "under": [123], "our": [124, 131], "framework.": [125], "Across": [126], "standard": [127], "datasets,": [130], "analysis": [132], "uncovers": [133], "statistically": [134], "significant": [135], "differences": [136], "fidelity": [139], "among": [140], "representative": [141], "LLM": [142], "families-even": [143], "is": [146], "comparable-highlighting": [147], "gaps": [148], "between": [149, 160], "final-answer": [150], "accuracy": [151], "derivation.": [154], "Our": [155, 174], "framework": [156], "provides": [157], "balance": [159], "free-form": [161], "formal": [164], "proofs": [165], "systems,": [166], "offering": [167], "actionable": [168], "diagnostics": [169], "for": [170], "evaluation.": [173], "code": [177], "are": [178], "available": [179], "at": [180], "https://github.com/YuanheZ/DAG-MATH.": [181]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5121999979019165, "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": 0.5121999979019165, "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/T13523", "display_name": "Mathematics, Computing, and Information Processing", "score": 0.10499999672174454, "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/T12522", "display_name": "Mathematics Education and Pedagogy", "score": 0.07850000262260437, "subfield": {"id": "https://openalex.org/subfields/2604", "display_name": "Applied Mathematics"}, "field": {"id": "https://openalex.org/fields/26", "display_name": "Mathematics"}, "domain": {"id": "https://openalex.org/domains/3", "display_name": "Physical Sciences"}}], "primary_location": {"id": "pmh:oai:arXiv.org:2510.19842", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.19842", "pdf_url": "https://arxiv.org/pdf/2510.19842", "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/W4415970861", "doi": "https://doi.org/10.1109/tmc.2025.3629736", "title": "ENWAR 2.0: An Agentic Multimodal Wireless LLM Framework With Reasoning, Situation-Aware Explainability and Beam Tracking", "publication_year": 2025, "publication_date": "2025-11-06", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5111108641", "display_name": "Ahmad M. Nazar", "orcid": "https://orcid.org/0000-0002-3264-6645", "observed_orcids": ["https://orcid.org/0000-0002-3264-6645"]}, "institutions": [{"id": "https://openalex.org/I173911158", "display_name": "Iowa State University", "ror": "https://ror.org/04rswrd78", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I173911158"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Ahmad M. Nazar", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA"], "raw_orcid": "https://orcid.org/0000-0002-3264-6645", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA", "institution_ids": ["https://openalex.org/I173911158"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5034034574", "display_name": "Abdulkadir \u00c7elik", "orcid": "https://orcid.org/0000-0001-9007-9979", "observed_orcids": ["https://orcid.org/0000-0001-9007-9979"]}, "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": "Abdulkadir Celik", "raw_affiliation_strings": ["School of Electronics and Computer Science, University of Southampton, Southampton, U.K"], "raw_orcid": "https://orcid.org/0000-0001-9007-9979", "affiliations": [{"raw_affiliation_string": "School of Electronics and Computer Science, University of Southampton, Southampton, U.K", "institution_ids": ["https://openalex.org/I43439940"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024301241", "display_name": "Mohamed Y. Selim", "orcid": "https://orcid.org/0000-0001-6695-370X", "observed_orcids": ["https://orcid.org/0000-0001-6695-370X"]}, "institutions": [{"id": "https://openalex.org/I173911158", "display_name": "Iowa State University", "ror": "https://ror.org/04rswrd78", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I173911158"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Mohamed Y. Selim", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA"], "raw_orcid": "https://orcid.org/0000-0001-6695-370X", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA", "institution_ids": ["https://openalex.org/I173911158"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5046741256", "display_name": "Asmaa Abdallah", "orcid": "https://orcid.org/0000-0003-3387-9333", "observed_orcids": ["https://orcid.org/0000-0003-3387-9333"]}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Asmaa Abdallah", "raw_affiliation_strings": ["Computer, Electrical, and Mathematical Sciences &#x0026; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "Computer, Electrical, and Mathematical Sciences &amp; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, KSA"], "raw_orcid": "https://orcid.org/0000-0003-3387-9333", "affiliations": [{"raw_affiliation_string": "Computer, Electrical, and Mathematical Sciences &#x0026; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer, Electrical, and Mathematical Sciences &amp; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, KSA", "institution_ids": ["https://openalex.org/I71920554"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5079810736", "display_name": "Daji Qiao", "orcid": "https://orcid.org/0000-0002-3662-6481", "observed_orcids": ["https://orcid.org/0000-0002-3662-6481"]}, "institutions": [{"id": "https://openalex.org/I173911158", "display_name": "Iowa State University", "ror": "https://ror.org/04rswrd78", "country_code": "US", "type": "education", "lineage": ["https://openalex.org/I173911158"]}], "countries": ["US"], "is_corresponding": false, "raw_author_name": "Daji Qiao", "raw_affiliation_strings": ["Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA"], "raw_orcid": "https://orcid.org/0000-0002-3662-6481", "affiliations": [{"raw_affiliation_string": "Department of Electrical and Computer Engineering, Iowa State University of Science and Technology, Ames, IA, USA", "institution_ids": ["https://openalex.org/I173911158"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5013660772", "display_name": "Ahmed M. Eltawil", "orcid": "https://orcid.org/0000-0003-1849-083X", "observed_orcids": ["https://orcid.org/0000-0003-1849-083X"]}, "institutions": [{"id": "https://openalex.org/I71920554", "display_name": "King Abdullah University of Science and Technology", "ror": "https://ror.org/01q3tbs38", "country_code": "SA", "type": "education", "lineage": ["https://openalex.org/I71920554"]}], "countries": ["SA"], "is_corresponding": false, "raw_author_name": "Ahmed M. Eltawil", "raw_affiliation_strings": ["Computer, Electrical, and Mathematical Sciences &#x0026; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "Computer, Electrical, and Mathematical Sciences &amp; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, KSA"], "raw_orcid": "https://orcid.org/0000-0003-1849-083X", "affiliations": [{"raw_affiliation_string": "Computer, Electrical, and Mathematical Sciences &#x0026; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia", "institution_ids": ["https://openalex.org/I71920554"]}, {"raw_affiliation_string": "Computer, Electrical, and Mathematical Sciences &amp; Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal, KSA", "institution_ids": ["https://openalex.org/I71920554"]}]}], "abstract_inverted_index": {"The": [0, 76], "evolution": [1], "of": [2, 62, 134], "next-generation": [3], "wireless": [4, 43], "networks": [5], "demands": [6], "intelligent,": [7], "adaptive,": [8], "and": [9, 35, 41, 56, 71, 86, 103, 119, 137, 148, 188, 206], "explainable": [10, 42], "decision-making": [11], "for": [12, 105, 124, 129, 140], "robust": [13], "communication": [14], "in": [15], "dynamic": [16, 91, 142], "environments.": [17], "This": [18], "paper": [19], "presentsEnwar": [20], "2.0,": [21], "the": [22, 73, 96, 131, 156, 193, 207, 225], "first": [23], "agentic": [24], "large": [25], "language": [26], "model": [27], "(LLM)": [28], "framework": [29], "integrating": [30], "adaptive": [31, 199, 229], "retrieval-augmented": [32], "generation": [33], "(RAG)": [34], "chain-of-thought": [36], "(CoT)": [37], "reasoning": [38, 102], "into": [39], "situation-aware": [40, 101], "network": [44], "management.Enwar": [45], "2.0introduces": [46], "two": [47], "specialized": [48], "agents:": [49], "a": [50], "transformer-fusion": [51], "(TransFusion)-based": [52], "beam": [53, 77, 84, 106, 157, 170], "prediction": [54, 78, 158], "agent": [55, 79, 99, 159], "an": [57], "environment": [58, 97], "perception": [59, 98], "agent,": [60], "both": [61], "which": [63, 112], "fuse": [64], "multi-modal": [65, 132], "sensory": [66], "inputs\u2014including": [67], "camera,": [68], "LiDAR,": [69], "radar,": [70], "GPS\u2014from": [72], "DeepSense6G": [74], "dataset.": [75], "enables": [80], "infrastructure-to-vehicle": [81], "(I2V)": [82], "target-in-the-loop": [83], "tracking": [85], "real-time": [87], "adaptation": [88], "based": [89], "on": [90, 114], "environmental": [92], "conditions.": [93], "In": [94, 191], "contrast,": [95], "provides": [100], "justifications": [104], "decisions.": [107], "Unlike": [108], "its": [109, 228], "predecessor,Enwar": [110], "1.0,": [111], "relied": [113], "static": [115, 239], "knowledge": [116], "bases": [117], "(KBs)": [118], "text-only": [120], "LLMs,Enwar": [121], "2.0is": [122], "designed": [123], "CoT": [125], "reasoning,": [126], "leverages": [127], "LLaMa3.2-3B/LLaMa3.1-8B/LLaMa3.3-70B": [128], "text-generation,": [130], "capabilities": [133], "LLaMa": [135], "3.2,": [136], "employs": [138], "LlamaIndex": [139], "fine-grained,": [141], "context": [143], "retrieval,": [144], "eliminating": [145], "retrieval": [146], "ambiguities": [147], "enhancing": [149], "response": [150], "relevance.": [151], "Numerical": [152], "results": [153], "show": [154], "that": [155], "achieves": [160, 201], "up": [161, 181, 202, 234], "to": [162, 182, 203, 224, 235, 238], "90.0%": [163], "Top-3": [164], "accuracy": [165], "at$t+3$,": [166], "effectively": [167], "predicting": [168], "optimal": [169], "selections": [171], "three": [172], "time": [173, 219], "steps": [174], "ahead.": [175], "Overall,Enwar": [176], "2.0achieves": [177], "state-of-the-art": [178], "performance,": [179], "with": [180], "89.7%/83.5%": [183], "interpretation/perception": [184], "correctness,": [185, 205], "81.6%/80.9%": [186], "faithfulness,": [187], "89.9%/88.2%": [189], "relevancy.": [190], "comparison,": [192], "baseline": [194, 208], "pretrained": [195], "LLaMa3": [196], "models": [197], "without": [198, 209], "RAG": [200, 210, 230], "80.3%/77.3%": [204], "performs": [211], "significantly": [212], "worse": [213], "at": [214], "67.1%/64.8%.": [215], "Additionally,Enwar": [216], "2.0reduces": [217], "processing": [218], "by": [220, 233], "over": [221], "100%": [222], "relative": [223], "baseline,": [226], "while": [227], "improves": [231], "performance": [232], "13.7%": [236], "compared": [237], "RAG.": [240]}, "primary_topic": {"id": "https://openalex.org/T10936", "display_name": "Millimeter-Wave Propagation and Modeling", "score": 0.23160000145435333, "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"}}, "topics": [{"id": "https://openalex.org/T10936", "display_name": "Millimeter-Wave Propagation and Modeling", "score": 0.23160000145435333, "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"}}, {"id": "https://openalex.org/T11458", "display_name": "Advanced Wireless Communication Technologies", "score": 0.11819999665021896, "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"}}, {"id": "https://openalex.org/T11714", "display_name": "Multimodal Machine Learning Applications", "score": 0.10189999639987946, "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/tmc.2025.3629736", "is_oa": false, "landing_page_url": "https://doi.org/10.1109/tmc.2025.3629736", "pdf_url": null, "source": {"id": "https://openalex.org/S69141925", "display_name": "IEEE Transactions on Mobile Computing", "issn_l": "1536-1233", "issn": ["1536-1233", "1558-0660", "2161-9875"], "is_oa": false, "is_in_doaj": false, "is_core": true, "listed_in": ["cwts-core", "jufo-3", "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 Mobile Computing", "raw_type": "journal-article"}, "cited_by_count": 0, "is_retracted": false}, {"id": "https://openalex.org/W4416269536", "doi": "https://doi.org/10.48550/arxiv.2511.04869", "title": "Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs", "publication_year": 2025, "publication_date": "2025-11-06", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5110716768", "display_name": "Preetum Nakkiran", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Nakkiran, Preetum", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5076803200", "display_name": "Arwen Bradley", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Bradley, Arwen", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5050308555", "display_name": "Adam Goli\u0144ski", "orcid": "https://orcid.org/0000-0001-8603-1171", "observed_orcids": ["https://orcid.org/0000-0001-8603-1171"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Goli\u0144ski, Adam", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5021079415", "display_name": "Eug\u00e8ne Ndiaye", "orcid": "https://orcid.org/0000-0002-4898-434X", "observed_orcids": ["https://orcid.org/0000-0002-4898-434X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ndiaye, Eugene", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5035574656", "display_name": "Michael Kirchhof", "orcid": "https://orcid.org/0000-0003-4521-9391", "observed_orcids": ["https://orcid.org/0000-0003-4521-9391"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Kirchhof, Michael", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Williamson, Sinead", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Williamson, Sinead", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "often": [4], "lack": [5], "meaningful": [6], "confidence": [7, 28, 61], "estimates": [8], "for": [9, 81], "their": [10, 34, 146], "outputs.": [11], "While": [12], "base": [13, 52, 135], "LLMs": [14, 53, 136, 171], "are": [15, 54, 172], "known": [16], "to": [17, 71, 131], "exhibit": [18], "next-token": [19, 90], "calibration,": [20, 51, 184], "it": [21], "remains": [22], "unclear": [23], "whether": [24], "they": [25, 57, 142], "can": [26, 58, 143], "assess": [27, 60], "in": [29, 62, 208], "the": [30, 37, 197], "actual": [31], "meaning": [32], "of": [33, 49, 89, 109, 115, 121, 161, 201], "responses": [35], "beyond": [36], "token": [38], "level.": [39], "We": [40, 157], "find": [41], "that,": [42], "when": [43, 141, 202], "using": [44], "a": [45, 79, 87, 93, 106, 113, 119, 132, 155], "certain": [46], "sampling-based": [47], "notion": [48, 114], "semantic": [50, 83, 150, 205], "remarkably": [55], "well-calibrated:": [56], "meaningfully": [59], "open-domain": [63], "question-answering": [64, 176], "tasks,": [65, 177], "despite": [66], "not": [67], "being": [68], "explicitly": [69], "trained": [70], "do": [72], "so.": [73], "Our": [74], "main": [75], "theoretical": [76, 128], "contribution": [77], "establishes": [78], "mechanism": [80, 129], "why": [82, 204], "calibration": [84, 97, 116, 206], "emerges": [85, 207], "as": [86], "byproduct": [88], "prediction,": [91, 163], "leveraging": [92], "recent": [94], "connection": [95], "between": [96], "and": [98, 185, 203], "local": [99], "loss": [100], "optimality.": [101], "The": [102], "theory": [103], "relies": [104], "on": [105], "general": [107], "definition": [108], "\"B-calibration,\"": [110], "which": [111, 164], "is": [112], "parameterized": [117], "by": [118], "choice": [120], "equivalence": [122], "classes": [123, 152], "(semantic": [124], "or": [125], "otherwise).": [126], "This": [127], "leads": [130], "testable": [133], "prediction:": [134], "will": [137], "be": [138], "semantically": [139, 173], "calibrated": [140, 174], "easily": [144], "predict": [145], "own": [147], "distribution": [148], "over": [149], "answer": [151], "before": [153], "generating": [154], "response.": [156], "state": [158], "three": [159], "implications": [160], "this": [162, 183], "we": [165], "validate": [166], "through": [167], "experiments:": [168], "(1)": [169], "Base": [170], "across": [175], "(2)": [178], "RL": [179], "instruction-tuning": [180], "systematically": [181], "breaks": [182, 189], "(3)": [186], "chain-of-thought": [187], "reasoning": [188], "calibration.": [190], "To": [191], "our": [192, 194], "knowledge,": [193], "work": [195], "provides": [196], "first": [198], "principled": [199], "explanation": [200], "LLMs.": [209]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5967000126838684, "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": 0.5967000126838684, "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": 0.23839999735355377, "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": 0.04650000110268593, "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:2511.04869", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.04869", "pdf_url": "https://arxiv.org/pdf/2511.04869", "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/W4416843434", "doi": "https://doi.org/10.48550/arxiv.2505.20170", "title": "Program of Equations Thoughts to Solve Algebra Word Problems", "publication_year": 2025, "publication_date": "2025-05-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5101247632", "display_name": "Yunze Lin", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I139759216", "display_name": "Beijing University of Posts and Telecommunications", "ror": "https://ror.org/04w9fbh59", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I139759216"]}], "countries": ["CN"], "is_corresponding": true, "raw_author_name": "Lin, Yunze", "raw_affiliation_strings": ["School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing", "institution_ids": ["https://openalex.org/I139759216"]}]}], "abstract_inverted_index": {"Solving": [0], "algebraic": [1], "word": [2], "problems": [3], "(AWPs)": [4], "has": [5, 35], "recently": [6], "emerged": [7], "as": [8], "an": [9], "important": [10], "natural": [11], "language": [12, 17], "processing": [13], "task.": [14], "Recently,": [15], "large": [16], "models": [18], "(LLMs)": [19], "have": [20], "demonstrated": [21], "powerful": [22], "mathematical": [23], "capabilities,": [24], "and": [25, 88, 132, 137], "the": [26, 46, 74, 135, 150, 156], "Chain-of-Thought": [27], "technique,": [28], "which": [29, 72, 109], "guides": [30], "LLMs": [31, 50, 117], "through": [32], "step-by-step": [33, 78], "reasoning,": [34], "yielded": [36], "impressive": [37], "results.": [38], "However,": [39], "this": [40], "reasoning": [41, 79], "ability": [42], "is": [43], "limited": [44], "by": [45], "computational": [47], "weaknesses": [48], "of": [49, 68, 76, 85, 130, 153], "themselves,": [51], "where": [52], "calculation": [53, 100], "errors": [54, 101], "can": [55], "accumulate,": [56], "leading": [57], "to": [58, 94, 98, 115, 118], "incorrect": [59], "final": [60], "answers.": [61], "To": [62], "address": [63], "this,": [64], "we": [65, 105], "propose": [66, 106], "Program": [67], "Equations": [69], "Thoughts": [70], "(POET),": [71], "transforms": [73], "task": [75, 84], "generating": [77, 89], "answers": [80], "into": [81], "a": [82, 95, 111, 142], "two-stage": [83], "predicting": [86], "equations": [87], "code,": [90], "offloading": [91], "complex": [92], "computations": [93], "Python": [96, 121], "interpreter": [97], "avoid": [99], "in": [102], "LLMs.": [103], "Furthermore,": [104], "Zero-shot": [107, 146], "POET,": [108], "utilizes": [110], "manually": [112], "designed": [113], "template": [114], "enable": [116], "directly": [119], "generate": [120], "code": [122], "for": [123], "one-step": [124], "solving.": [125], "Our": [126], "method": [127], "achieves": [128, 149], "accuracies": [129], "95.3%": [131], "98.0%": [133], "on": [134, 155], "PEN": [136], "ALG514": [138], "datasets,": [139], "respectively,": [140], "setting": [141], "new": [143], "state-of-the-art": [144], "(SOTA).": [145], "POET": [147], "also": [148], "SOTA": [151], "result": [152], "95.5%": [154], "DRAW-1K": [157], "dataset.": [158]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.75, "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": 0.75, "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": 0.16539999842643738, "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/T13523", "display_name": "Mathematics, Computing, and Information Processing", "score": 0.024000000208616257, "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": "pmh:oai:arXiv.org:2505.20170", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2505.20170", "pdf_url": "https://arxiv.org/pdf/2505.20170", "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/W4416074961", "doi": "https://doi.org/10.48550/arxiv.2506.04098", "title": "TextAtari: 100K Frames Game Playing with Language Agents", "publication_year": 2025, "publication_date": "2025-06-04", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5100362638", "display_name": "Wenhao Li", "orcid": "https://orcid.org/0000-0003-2985-1098", "observed_orcids": ["https://orcid.org/0000-0003-2985-1098"]}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Li, Wenhao", "raw_affiliation_strings": ["Tongji University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tongji University , Shanghai , China", "institution_ids": ["https://openalex.org/I116953780"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5004479175", "display_name": "Wenwu Li", "orcid": "https://orcid.org/0009-0004-9772-9283", "observed_orcids": ["https://orcid.org/0009-0004-9772-9283"]}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Li, Wenwu", "raw_affiliation_strings": ["Tongji University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tongji University , Shanghai , China", "institution_ids": ["https://openalex.org/I116953780"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5067981458", "display_name": "Chuyun Shen", "orcid": "https://orcid.org/0009-0001-3622-1193", "observed_orcids": ["https://orcid.org/0009-0001-3622-1193"]}, "institutions": [{"id": "https://openalex.org/I66867065", "display_name": "East China Normal University", "ror": "https://ror.org/02n96ep67", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I66867065"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Shen, Chuyun", "raw_affiliation_strings": ["East China Normal University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "East China Normal University , Shanghai , China", "institution_ids": ["https://openalex.org/I66867065"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5087962706", "display_name": "Junjie Sheng", "orcid": "https://orcid.org/0000-0002-3766-9870", "observed_orcids": ["https://orcid.org/0000-0002-3766-9870"]}, "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": "Sheng, Junjie", "raw_affiliation_strings": ["Huawei Cloud Huawei Technologies Co., Ltd. , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Huawei Cloud Huawei Technologies Co., Ltd. , Shanghai , China", "institution_ids": ["https://openalex.org/I2250955327"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085141282", "display_name": "Zixiao Huang", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I66867065", "display_name": "East China Normal University", "ror": "https://ror.org/02n96ep67", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I66867065"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Huang, Zixiao", "raw_affiliation_strings": ["East China Normal University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "East China Normal University , Shanghai , China", "institution_ids": ["https://openalex.org/I66867065"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102968088", "display_name": "Di Wu", "orcid": "https://orcid.org/0000-0003-0228-5284", "observed_orcids": ["https://orcid.org/0000-0003-0228-5284"]}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wu, Di", "raw_affiliation_strings": ["Tongji University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tongji University , Shanghai , China", "institution_ids": ["https://openalex.org/I116953780"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101519280", "display_name": "Yun Hua", "orcid": "https://orcid.org/0000-0002-1703-9775", "observed_orcids": ["https://orcid.org/0000-0002-1703-9775"]}, "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"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Hua, Yun", "raw_affiliation_strings": ["Shanghai Jiao Tong University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Shanghai Jiao Tong University , Shanghai , China", "institution_ids": ["https://openalex.org/I183067930"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100777418", "display_name": "Wei Yin", "orcid": "https://orcid.org/0000-0003-0432-4355", "observed_orcids": ["https://orcid.org/0000-0003-0432-4355", "https://orcid.org/0009-0006-6741-9529"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yin, Wei", "raw_affiliation_strings": ["Bank of Communications , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Bank of Communications , Shanghai , China", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5101927070", "display_name": "Xiangfeng Wang", "orcid": "https://orcid.org/0000-0003-3064-5128", "observed_orcids": ["https://orcid.org/0000-0003-3064-5128", "https://orcid.org/0000-0003-1802-4425"]}, "institutions": [{"id": "https://openalex.org/I66867065", "display_name": "East China Normal University", "ror": "https://ror.org/02n96ep67", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I66867065"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Wang, Xiangfeng", "raw_affiliation_strings": ["East China Normal University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "East China Normal University , Shanghai , China", "institution_ids": ["https://openalex.org/I66867065"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5046703129", "display_name": "Hongyuan Zha", "orcid": "https://orcid.org/0000-0001-7493-0911", "observed_orcids": ["https://orcid.org/0000-0001-7493-0911"]}, "institutions": [{"id": "https://openalex.org/I4210116924", "display_name": "Chinese University of Hong Kong, Shenzhen", "ror": "https://ror.org/02d5ks197", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I177725633", "https://openalex.org/I180726961", "https://openalex.org/I4210116924"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Zha, Hongyuan", "raw_affiliation_strings": ["The Chinese University of Hong Kong , Shenzhen , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "The Chinese University of Hong Kong , Shenzhen , China", "institution_ids": ["https://openalex.org/I4210116924"]}]}, {"author_position": "last", "author": {"id": null, "display_name": "Jin, Bo", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I116953780", "display_name": "Tongji University", "ror": "https://ror.org/03rc6as71", "country_code": "CN", "type": "education", "lineage": ["https://openalex.org/I116953780"]}], "countries": ["CN"], "is_corresponding": false, "raw_author_name": "Jin, Bo", "raw_affiliation_strings": ["Tongji University , Shanghai , China"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Tongji University , Shanghai , China", "institution_ids": ["https://openalex.org/I116953780"]}]}], "abstract_inverted_index": {"We": [0, 73], "present": [1], "TextAtari,": [2], "a": [3, 35, 168], "benchmark": [4, 48], "for": [5, 170], "evaluating": [6], "language": [7, 45, 78, 135, 177], "agents": [8, 136], "on": [9, 104, 125], "very": [10], "long-horizon": [11, 106], "decision-making": [12, 42], "tasks": [13, 53], "spanning": [14], "up": [15], "to": [16, 94], "100,000": [17], "steps.": [18, 159], "By": [19], "translating": [20], "the": [21, 115, 174], "visual": [22], "state": [23, 149], "representations": [24], "of": [25, 99, 117, 156, 158, 176], "classic": [26], "Atari": [27], "games": [28], "into": [29], "rich": [30], "textual": [31], "descriptions,": [32], "TextAtari": [33, 160], "creates": [34], "challenging": [36], "test": [37], "bed": [38], "that": [39], "bridges": [40], "sequential": [41, 147], "with": [43, 54], "natural": [44], "processing.": [46], "The": [47], "includes": [49], "nearly": [50], "100": [51], "distinct": [52], "varying": [55], "complexity,": [56], "action": [57], "spaces,": [58], "and": [59, 82, 91, 113, 122, 137, 151, 167, 179], "planning": [60, 142, 153], "horizons,": [61], "all": [62], "rendered": [63], "as": [64], "text": [65], "through": [66], "an": [67], "unsupervised": [68], "representation": [69], "learning": [70], "framework": [71, 169], "(AtariARI).": [72], "evaluate": [74], "three": [75, 85], "open-source": [76], "large": [77], "models": [79, 178], "(Qwen2.5-7B,": [80], "Gemma-7B,": [81], "Llama3.1-8B)": [83], "across": [84, 154], "agent": [86, 126], "frameworks": [87], "(zero-shot,": [88], "few-shot": [89], "chain-of-thought,": [90], "reflection": [92], "reasoning)": [93], "assess": [95], "how": [96], "different": [97], "forms": [98], "prior": [100], "knowledge": [101], "affect": [102], "performance": [103, 132], "these": [105], "challenges.": [107], "Four": [108], "scenarios-Basic,": [109], "Obscured,": [110], "Manual": [111], "Augmentation,": [112], "Reference-based-investigate": [114], "impact": [116], "semantic": [118], "understanding,": [119], "instruction": [120], "comprehension,": [121], "expert": [123], "demonstrations": [124], "decision-making.": [127], "Our": [128, 181], "results": [129], "reveal": [130], "significant": [131], "gaps": [133], "between": [134], "human": [138], "players": [139], "in": [140, 146], "extensive": [141], "tasks,": [143], "highlighting": [144], "challenges": [145], "reasoning,": [148], "tracking,": [150], "strategic": [152], "tens": [155], "thousands": [157], "provides": [161], "standardized": [162], "evaluation": [163], "protocols,": [164], "baseline": [165], "implementations,": [166], "advancing": [171], "research": [172], "at": [173, 185], "intersection": [175], "planning.": [180], "code": [182], "is": [183], "available": [184], "https://github.com/Lww007/Text-Atari-Agents.": [186]}, "primary_topic": {"id": "https://openalex.org/T11574", "display_name": "Artificial Intelligence in Games", "score": 0.42480000853538513, "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/T11574", "display_name": "Artificial Intelligence in Games", "score": 0.42480000853538513, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.2824999988079071, "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": 0.08269999921321869, "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:2506.04098", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2506.04098", "pdf_url": "https://arxiv.org/pdf/2506.04098", "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/W4416124989", "doi": "https://doi.org/10.48550/arxiv.2504.03930", "title": "Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition", "publication_year": 2025, "publication_date": "2025-04-04", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5070202776", "display_name": "Rishi Hazra", "orcid": "https://orcid.org/0000-0003-3422-2085", "observed_orcids": ["https://orcid.org/0000-0003-3422-2085"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hazra, Rishi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5013733673", "display_name": "Gabriele Venturato", "orcid": "https://orcid.org/0000-0002-0048-0898", "observed_orcids": ["https://orcid.org/0000-0002-0048-0898"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Venturato, Gabriele", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5002794832", "display_name": "Pedro Zuidberg Dos Martires", "orcid": "https://orcid.org/0000-0001-5834-0188", "observed_orcids": ["https://orcid.org/0000-0001-5834-0188"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Martires, Pedro Zuidberg Dos", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5078136609", "display_name": "Luc De Raedt", "orcid": "https://orcid.org/0000-0002-6860-6303", "observed_orcids": ["https://orcid.org/0000-0002-6860-6303"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "De Raedt, Luc", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4], "been": [5], "touted": [6], "as": [7], "AI": [8], "models": [9, 141], "possessing": [10], "advanced": [11], "reasoning": [12, 29, 55, 86, 103, 177], "abilities.": [13], "In": [14], "theory,": [15], "autoregressive": [16], "LLMs": [17, 39, 107], "with": [18, 121], "Chain-of-Thought": [19], "(CoT)": [20], "can": [21], "perform": [22], "more": [23], "serial": [24], "computations": [25], "to": [26, 44], "solve": [27], "complex": [28], "tasks.": [30, 90], "However,": [31], "recent": [32], "studies": [33], "suggest": [34, 185], "that,": [35], "despite": [36], "this": [37], "capacity,": [38], "do": [40], "not": [41], "truly": [42], "learn": [43], "reason": [45], "but": [46], "instead": [47], "fit": [48], "on": [49, 73, 135], "statistical": [50, 144], "features.": [51], "To": [52], "study": [53, 167], "the": [54, 76, 82, 94, 102, 110, 114, 158, 170], "capabilities": [56], "in": [57, 97, 175], "a": [58, 63, 162], "principled": [59, 163], "fashion,": [60], "we": [61, 92], "adopt": [62], "computational": [64], "theory": [65], "perspective": [66], "and": [67, 87, 100, 184], "propose": [68], "an": [69], "experimental": [70, 164], "protocol": [71], "centered": [72], "3-SAT": [74, 99], "--": [75], "prototypical": [77], "NP-complete": [78], "problem": [79, 115], "lying": [80], "at": [81], "core": [83], "of": [84, 105, 113, 155], "logical": [85], "constraint": [88], "satisfaction": [89], "Specifically,": [91], "examine": [93], "phase": [95], "transitions": [96], "random": [98], "characterize": [101], "abilities": [104], "state-of-the-art": [106], "by": [108], "varying": [109], "inherent": [111], "hardness": [112], "instances.": [116], "By": [117], "comparing": [118], "DeepSeek": [119], "R1": [120, 152], "other": [122, 150], "LLMs,": [123, 151], "our": [124, 166], "findings": [125, 180], "reveal": [126], "two": [127], "key": [128], "insights": [129], "(1)": [130], "LLM": [131, 176], "accuracy": [132], "drops": [133], "significantly": [134], "harder": [136], "instances,": [137], "suggesting": [138], "all": [139], "current": [140], "struggle": [142], "when": [143], "shortcuts": [145], "are": [146], "unavailable": [147], "(2)": [148], "Unlike": [149], "shows": [153], "signs": [154], "having": [156], "learned": [157], "underlying": [159], "reasoning.": [160], "Following": [161], "protocol,": [165], "moves": [168], "beyond": [169], "benchmark-driven": [171], "evidence": [172], "often": [173], "found": [174], "research.": [178, 190], "Our": [179], "highlight": [181], "important": [182], "gaps": [183], "clear": [186], "directions": [187], "for": [188], "future": [189]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.5077999830245972, "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": 0.5077999830245972, "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/T11596", "display_name": "Constraint Satisfaction and Optimization", "score": 0.2168000042438507, "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/T11010", "display_name": "Logic, Reasoning, and Knowledge", "score": 0.08229999989271164, "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:2504.03930", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2504.03930", "pdf_url": "https://arxiv.org/pdf/2504.03930", "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/W4414108623", "doi": "https://doi.org/10.1007/s10278-025-01659-4", "title": "Implementing a Resource-Light and Low-Code Large Language Model System for Information Extraction from Mammography Reports: A Pilot Study", "publication_year": 2025, "publication_date": "2025-09-10", "type": "article", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5020748054", "display_name": "Fabio Dennst\u00e4dt", "orcid": "https://orcid.org/0000-0002-5374-8720", "observed_orcids": ["https://orcid.org/0000-0002-5374-8720"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I202963720", "display_name": "University of St.Gallen", "ror": "https://ror.org/0561a3s31", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I202963720"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": true, "raw_author_name": "Fabio Dennst\u00e4dt", "raw_affiliation_strings": ["Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland. fabio.dennstaedt@insel.ch", "School of Medicine, University of St. Gallen, St. Gallen, Switzerland. fabio.dennstaedt@insel.ch", "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": "https://orcid.org/0000-0002-5374-8720", "affiliations": [{"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland. fabio.dennstaedt@insel.ch", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}, {"raw_affiliation_string": "School of Medicine, University of St. Gallen, St. Gallen, Switzerland. fabio.dennstaedt@insel.ch", "institution_ids": ["https://openalex.org/I202963720"]}, {"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Simon Fauser", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Simon Fauser", "raw_affiliation_strings": ["Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5019550666", "display_name": "Nikola \u010cihori\u0107", "orcid": "https://orcid.org/0000-0003-1534-8520", "observed_orcids": ["https://orcid.org/0000-0003-1534-8520"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Nikola Cihoric", "raw_affiliation_strings": ["Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5115007095", "display_name": "Max Schmerder", "orcid": "https://orcid.org/0009-0009-3663-4412", "observed_orcids": ["https://orcid.org/0009-0009-3663-4412"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Max Schmerder", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}, {"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102952833", "display_name": "Paolo Lombardo", "orcid": "https://orcid.org/0000-0002-4879-2866", "observed_orcids": ["https://orcid.org/0000-0002-4879-2866"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Paolo Lombardo", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5084440057", "display_name": "Grazia M. Cereghetti", "orcid": "https://orcid.org/0009-0005-2228-8169", "observed_orcids": ["https://orcid.org/0009-0005-2228-8169"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Grazia Maria Cereghetti", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114568995", "display_name": "Sandro Urs von D\u00e4niken", "orcid": "https://orcid.org/0009-0007-2169-9438", "observed_orcids": ["https://orcid.org/0009-0007-2169-9438"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Sandro von D\u00e4niken", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Thomas Minder", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Thomas Minder", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": null, "display_name": "Jaro Meyer", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Jaro Meyer", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5037223512", "display_name": "Lawrence Chiang", "orcid": "https://orcid.org/0009-0006-3961-8280", "observed_orcids": ["https://orcid.org/0009-0006-3961-8280", "https://orcid.org/0009-0004-5267-6237"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Lawrence Chiang", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5114568996", "display_name": "Roberto Gaio", "orcid": "https://orcid.org/0009-0009-9840-1366", "observed_orcids": ["https://orcid.org/0009-0009-9840-1366"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Roberto Gaio", "raw_affiliation_strings": ["Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5107584988", "display_name": "Luc Lerch", "orcid": null, "observed_orcids": []}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Luc Lerch", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5091045806", "display_name": "Irina Filchenko", "orcid": "https://orcid.org/0000-0002-9486-1017", "observed_orcids": ["https://orcid.org/0000-0002-9486-1017"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Irina Filchenko", "raw_affiliation_strings": ["Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5086130468", "display_name": "Daniel Reichenpfader", "orcid": "https://orcid.org/0000-0002-8052-3359", "observed_orcids": ["https://orcid.org/0000-0002-8052-3359"]}, "institutions": [{"id": "https://openalex.org/I114457229", "display_name": "University of Geneva", "ror": "https://ror.org/01swzsf04", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I114457229"]}, {"id": "https://openalex.org/I130692619", "display_name": "Bern University of Applied Sciences", "ror": "https://ror.org/02bnkt322", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I130692619"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Daniel Reichenpfader", "raw_affiliation_strings": ["Faculty of Medicine, University of Geneva, Geneva, Switzerland", "Institute for Patient-Centered Digital Health, Bern University of Applied Sciences, Biel/Bienne, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Faculty of Medicine, University of Geneva, Geneva, Switzerland", "institution_ids": ["https://openalex.org/I114457229"]}, {"raw_affiliation_string": "Institute for Patient-Centered Digital Health, Bern University of Applied Sciences, Biel/Bienne, Switzerland", "institution_ids": ["https://openalex.org/I130692619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5024787898", "display_name": "Kerstin Denecke", "orcid": "https://orcid.org/0000-0001-6691-396X", "observed_orcids": ["https://orcid.org/0000-0001-6691-396X"]}, "institutions": [{"id": "https://openalex.org/I130692619", "display_name": "Bern University of Applied Sciences", "ror": "https://ror.org/02bnkt322", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I130692619"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Kerstin Denecke", "raw_affiliation_strings": ["Institute for Patient-Centered Digital Health, Bern University of Applied Sciences, Biel/Bienne, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Patient-Centered Digital Health, Bern University of Applied Sciences, Biel/Bienne, Switzerland", "institution_ids": ["https://openalex.org/I130692619"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117107544", "display_name": "Caslav Vojvodic", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Caslav Vojvodic", "raw_affiliation_strings": ["Wemedoo AG, Steinhausen, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Wemedoo AG, Steinhausen, Switzerland", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5117107545", "display_name": "Igor Tatalovic", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Igor Tatalovic", "raw_affiliation_strings": ["Wemedoo AG, Steinhausen, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Wemedoo AG, Steinhausen, Switzerland", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5109401898", "display_name": "Andr\u00e9 Sander", "orcid": "https://orcid.org/0000-0002-1843-3125", "observed_orcids": ["https://orcid.org/0000-0002-1843-3125"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Andr\u00e9 Sander", "raw_affiliation_strings": ["ID Berlin GmbH, Berlin, Germany"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "ID Berlin GmbH, Berlin, Germany", "institution_ids": []}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5044072805", "display_name": "Janna Hastings", "orcid": "https://orcid.org/0000-0002-3469-4923", "observed_orcids": ["https://orcid.org/0000-0002-3469-4923"]}, "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/I202697423", "display_name": "University of Zurich", "ror": "https://ror.org/02crff812", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I202697423"]}, {"id": "https://openalex.org/I202963720", "display_name": "University of St.Gallen", "ror": "https://ror.org/0561a3s31", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I202963720"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Janna Hastings", "raw_affiliation_strings": ["Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland", "School of Medicine, University of St. Gallen, St. Gallen, Switzerland", "Swiss Institute of Bioinformatics, Lausanne, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland", "institution_ids": ["https://openalex.org/I202697423"]}, {"raw_affiliation_string": "School of Medicine, University of St. Gallen, St. Gallen, Switzerland", "institution_ids": ["https://openalex.org/I202963720"]}, {"raw_affiliation_string": "Swiss Institute of Bioinformatics, Lausanne, Switzerland", "institution_ids": ["https://openalex.org/I12708293"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5085777557", "display_name": "Daniel M. Aebersold", "orcid": "https://orcid.org/0000-0002-9493-3834", "observed_orcids": ["https://orcid.org/0000-0002-9493-3834"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Daniel M Aebersold", "raw_affiliation_strings": ["Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5031063057", "display_name": "Hendrik von Tengg\u2010Kobligk", "orcid": "https://orcid.org/0000-0003-3207-3223", "observed_orcids": ["https://orcid.org/0000-0003-3207-3223"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Hendrik von Tengg-Kobligk", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}, {"author_position": "last", "author": {"id": "https://openalex.org/A5008367053", "display_name": "Knud Nairz", "orcid": "https://orcid.org/0000-0003-3337-110X", "observed_orcids": ["https://orcid.org/0000-0003-3337-110X"]}, "institutions": [{"id": "https://openalex.org/I118564535", "display_name": "University of Bern", "ror": "https://ror.org/02k7v4d05", "country_code": "CH", "type": "education", "lineage": ["https://openalex.org/I118564535"]}, {"id": "https://openalex.org/I2801112126", "display_name": "University Hospital of Bern", "ror": "https://ror.org/01q9sj412", "country_code": "CH", "type": "healthcare", "lineage": ["https://openalex.org/I2801112126"]}], "countries": ["CH"], "is_corresponding": false, "raw_author_name": "Knud Nairz", "raw_affiliation_strings": ["Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland"], "raw_orcid": null, "affiliations": [{"raw_affiliation_string": "Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland", "institution_ids": ["https://openalex.org/I118564535", "https://openalex.org/I2801112126"]}]}], "abstract_inverted_index": {"Large": [0], "language": [1], "models": [2], "(LLMs)": [3], "have": [4], "been": [5], "successfully": [6], "used": [7, 92], "for": [8, 43, 93, 104, 123, 173, 230, 242], "data": [9, 44, 53, 94, 244], "extraction": [10, 45, 95], "from": [11, 46, 205], "free-text": [12, 47], "radiology": [13], "reports.": [14], "Most": [15], "current": [16], "studies": [17], "were": [18, 59, 72, 91, 102, 119], "conducted": [19, 120], "with": [20, 109, 176, 210], "LLMs": [21, 85, 144, 200], "accessed": [22], "via": [23], "an": [24, 62], "application": [25], "programming": [26], "interface": [27], "(API).": [28], "We": [29], "evaluated": [30], "the": [31, 97, 124, 143, 163, 191, 218, 243], "feasibility": [32], "of": [33, 111, 127, 147, 162, 178, 217], "using": [34, 50, 96, 121], "open-source": [35, 84, 199], "LLMs,": [36], "deployed": [37, 198], "on": [38, 87], "limited": [39, 211], "local": [40], "hardware": [41], "resources": [42], "mammography": [48, 206], "reports,": [49, 207], "a": [51, 88, 234], "common": [52], "element": [54], "(CDE)-based": [55], "structure.": [56], "Seventy-nine": [57], "CDEs": [58], "defined": [60], "by": [61, 74], "interdisciplinary": [63], "expert": [64], "panel,": [65], "reflecting": [66], "real-world": [67], "reporting": [68], "practice.": [69], "Sixty-one": [70], "reports": [71], "classified": [73], "two": [75], "independent": [76], "researchers": [77], "to": [78, 158, 166, 186, 194], "establish": [79], "ground": [80], "truth.": [81], "Five": [82], "different": [83, 106], "deployable": [86], "single": [89], "GPU": [90], "general-classifier": [98], "Python": [99], "package.": [100], "Extractions": [101], "performed": [103], "five": [105], "prompt": [107], "approaches": [108], "calculation": [110], "overall": [112], "accuracy,": [113], "micro-recall": [114], "and": [115, 215, 220, 240], "micro-F1.": [116], "Additional": [117], "analyses": [118], "thresholds": [122, 182], "relative": [125], "probability": [126], "classifications.": [128], "High": [129], "inter-rater": [130], "agreement": [131], "was": [132], "observed": [133], "between": [134], "manual": [135], "classifiers": [136], "(Cohen's": [137], "kappa": [138], "0.83).": [139], "Using": [140, 233], "default": [141, 164], "prompts,": [142], "achieved": [145], "accuracies": [146, 177, 185], "59.2-72.9%.": [148], "Chain-of-thought": [149], "prompting": [150, 156, 221], "yielded": [151], "mixed": [152], "results,": [153], "while": [154], "few-shot": [155], "led": [157], "decreased": [159], "accuracy.": [160], "Adaptation": [161], "prompts": [165], "precisely": [167], "define": [168], "classification": [169], "tasks": [170], "improved": [171, 184], "performance": [172], "all": [174], "models,": [175], "64.7-85.3%.": [179], "Setting": [180], "certainty": [181], "further": [183], ">": [187], "90%": [188], "but": [189], "reduced": [190], "coverage": [192], "rate": [193], "<": [195], "50%.": [196], "Locally": [197], "can": [201], "effectively": [202], "extract": [203], "information": [204], "maintaining": [208], "compatibility": [209], "computational": [212], "resources.": [213], "Selection": [214], "evaluation": [216], "model": [219], "strategy": [222], "are": [223], "critical.": [224], "Clear,": [225], "task-specific": [226], "instructions": [227], "appear": [228], "crucial": [229], "high": [231], "performance.": [232], "CDE-based": [235], "framework": [236], "provides": [237], "clear": [238], "semantics": [239], "structure": [241], "extraction.": [245]}, "primary_topic": {"id": "https://openalex.org/T11636", "display_name": "Artificial Intelligence in Healthcare and Education", "score": 0.3928000032901764, "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": 0.3928000032901764, "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/T11710", "display_name": "Biomedical Text Mining and Ontologies", "score": 0.16040000319480896, "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": 0.1378999948501587, "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/s10278-025-01659-4", "is_oa": true, "landing_page_url": "https://doi.org/10.1007/s10278-025-01659-4", "pdf_url": "https://link.springer.com/content/pdf/10.1007/s10278-025-01659-4.pdf", "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": "cc-by", "license_id": "https://openalex.org/licenses/cc-by", "version": "publishedVersion", "is_accepted": true, "is_published": true, "raw_source_name": "Journal of Imaging Informatics in Medicine", "raw_type": "journal-article"}, "cited_by_count": 4, "is_retracted": false}, {"id": "https://openalex.org/W7106782785", "doi": null, "title": "RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System", "publication_year": 2025, "publication_date": "2025-11-23", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Guan, Runwei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Guan, Runwei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Hu, Rongsheng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Hu, Rongsheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Chen, Shangshu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Shangshu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Xiao, Ningyuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xiao, Ningyuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Xia, Xue", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xia, Xue", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Liu, Jiayang", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Jiayang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Chen, Beibei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Beibei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Tang, Ziren", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tang, Ziren", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Ouyang, Ningwei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ouyang, Ningwei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Liang, Shaofeng", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liang, Shaofeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Fan, Yuxuan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Fan, Yuxuan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Sun, Wanjie", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Sun, Wanjie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": null, "display_name": "Yue, Yutao", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Yue, Yutao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Current": [0], "roadside": [1, 45], "perception": [2, 183], "systems": [3], "mainly": [4], "focus": [5], "on": [6, 146, 156], "instance-level": [7], "perception,": [8], "which": [9], "fall": [10], "short": [11], "in": [12, 23, 91, 180], "enabling": [13], "interaction": [14, 73], "via": [15, 139], "natural": [16], "language": [17], "and": [18, 34, 59, 72, 86, 95, 142, 158, 170, 184], "reasoning": [19, 102, 168, 185], "about": [20], "traffic": [21, 60, 76, 93, 182], "behaviors": [22], "context.": [24], "To": [25, 98], "bridge": [26], "this": [27], "gap,": [28], "we": [29, 110, 127, 149], "introduce": [30], "RoadSceneVQA,": [31], "a": [32, 116], "large-scale": [33], "richly": [35], "annotated": [36], "visual": [37], "question": [38], "answering": [39], "(VQA)": [40], "dataset": [41, 48], "specifically": [42], "tailored": [43], "for": [44], "scenarios.": [46], "The": [47], "comprises": [49], "34,736": [50], "diverse": [51], "QA": [52], "pairs": [53], "collected": [54], "under": [55], "varying": [56], "weather,": [57], "illumination,": [58], "conditions,": [61], "targeting": [62], "not": [63], "only": [64], "object": [65], "attributes": [66], "but": [67], "also": [68], "the": [69, 101, 129, 136, 147, 151, 163, 174], "intent,": [70], "legality,": [71], "patterns": [74], "of": [75, 104], "participants.": [77], "RoadSceneVQA": [78, 157], "challenges": [79], "models": [80], "to": [81, 134, 176], "perform": [82], "both": [83, 167], "explicit": [84], "recognition": [85], "implicit": [87], "commonsense": [88], "reasoning,": [89], "grounded": [90], "real-world": [92], "rules": [94], "contextual": [96], "dependencies.": [97], "fully": [99], "exploit": [100], "potential": [103], "Multi-modal": [105], "Large": [106], "Language": [107], "Models": [108], "(MLLMs),": [109], "further": [111], "propose": [112, 128, 150], "CogniAnchor": [113], "Fusion": [114], "(CAF),": [115], "vision-language": [117], "fusion": [118], "module": [119], "inspired": [120], "by": [121], "human-like": [122], "scene": [123], "anchoring": [124], "mechanisms.": [125], "Moreover,": [126], "Assisted": [130], "Decoupled": [131], "Chain-of-Thought": [132], "(AD-CoT)": [133], "enhance": [135], "reasoned": [137], "thinking": [138], "CoT": [140], "prompting": [141], "multi-task": [143], "learning.": [144], "Based": [145], "above,": [148], "baseline": [152], "model": [153], "RoadMind.": [154], "Experiments": [155], "CODA-LM": [159], "benchmark": [160], "show": [161], "that": [162], "pipeline": [164], "consistently": [165], "improves": [166], "accuracy": [169], "computational": [171], "efficiency,": [172], "allowing": [173], "MLLM": [175], "achieve": [177], "state-of-the-art": [178], "performance": [179], "structural": [181], "tasks.": [186]}, "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/T10036", "display_name": "Advanced Neural Network Applications", "score": 0.0020000000949949026, "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/T11099", "display_name": "Autonomous Vehicle Technology and Safety", "score": 0.0007999999797903001, "subfield": {"id": "https://openalex.org/subfields/2203", "display_name": "Automotive 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:2511.18286", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2511.18286", "pdf_url": "https://arxiv.org/pdf/2511.18286", "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/W4417295267", "doi": "https://doi.org/10.48550/arxiv.2512.10273", "title": "Reverse Thinking Enhances Missing Information Detection in Large Language Models", "publication_year": 2025, "publication_date": "2025-12-11", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5102519426", "display_name": "Yuxin Liu", "orcid": "https://orcid.org/0000-0002-0292-0834", "observed_orcids": ["https://orcid.org/0000-0002-0292-0834"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Yuxin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5074511454", "display_name": "Chaojie Gu", "orcid": "https://orcid.org/0000-0003-2153-811X", "observed_orcids": ["https://orcid.org/0000-0003-2153-811X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gu, Chaojie", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5034678630", "display_name": "Yihang Zhang", "orcid": "https://orcid.org/0009-0008-9446-5111", "observed_orcids": ["https://orcid.org/0009-0008-9446-5111", "https://orcid.org/0009-0000-3028-900X", "https://orcid.org/0009-0002-8759-8609", "https://orcid.org/0009-0003-6480-9888"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Yihang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Qian, Bin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Qian, Bin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5068195118", "display_name": "Shibo He", "orcid": "https://orcid.org/0000-0002-1505-6766", "observed_orcids": ["https://orcid.org/0000-0002-1505-6766"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "He, Shibo", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "have": [4, 41], "demonstrated": [5], "remarkable": [6], "capabilities": [7], "in": [8, 44], "various": [9], "reasoning": [10, 33, 119, 141, 153], "tasks,": [11], "yet": [12], "they": [13, 47], "often": [14], "struggle": [15], "with": [16], "problems": [17], "involving": [18], "missing": [19, 73, 102, 111], "information,": [20], "exhibiting": [21], "issues": [22], "such": [23], "as": [24], "incomplete": [25], "responses,": [26], "factual": [27], "errors,": [28], "and": [29, 38, 53, 100, 152], "hallucinations.": [30], "While": [31], "forward": [32, 140], "approaches": [34], "like": [35], "Chain-of-Thought": [36], "(CoT)": [37], "Tree-of-Thought": [39], "(ToT)": [40], "shown": [42], "success": [43], "structured": [45], "problem-solving,": [46], "frequently": [48], "fail": [49], "to": [50, 68, 96, 138], "systematically": [51], "identify": [52, 97], "recover": [54], "omitted": [55], "information.": [56], "In": [57], "this": [58], "paper,": [59], "we": [60, 85], "explore": [61], "the": [62, 107], "potential": [63], "of": [64, 110], "reverse": [65, 94, 130], "thinking": [66, 95, 131], "methodologies": [67], "enhance": [69], "LLMs'": [70, 149], "performance": [71, 135], "on": [72, 82], "information": [74, 112], "detection": [75], "tasks.": [76], "Drawing": [77], "inspiration": [78], "from": [79], "recent": [80], "work": [81], "backward": [83, 118], "reasoning,": [84], "propose": [86], "a": [87, 115, 144], "novel": [88], "framework": [89], "that": [90, 128], "guides": [91], "LLMs": [92], "through": [93], "necessary": [98], "conditions": [99], "pinpoint": [101], "elements.": [103], "Our": [104], "approach": [105, 132], "transforms": [106], "challenging": [108], "task": [109], "identification": [113], "into": [114], "more": [116], "manageable": [117], "problem,": [120], "significantly": [121], "improving": [122], "model": [123], "accuracy.": [124], "Experimental": [125], "results": [126], "demonstrate": [127], "our": [129], "achieves": [133], "substantial": [134], "gains": [136], "compared": [137], "traditional": [139], "methods,": [142], "providing": [143], "promising": [145], "direction": [146], "for": [147], "enhancing": [148], "logical": [150], "completeness": [151], "robustness.": [154]}, "primary_topic": {"id": "https://openalex.org/T10028", "display_name": "Topic Modeling", "score": 0.8633000254631042, "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": 0.8633000254631042, "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": 0.046799998730421066, "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": 0.0406000018119812, "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:2512.10273", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2512.10273", "pdf_url": "https://arxiv.org/pdf/2512.10273", "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/W4415967407", "doi": "https://doi.org/10.48550/arxiv.2510.18442", "title": "PlanU: Large Language Model Reasoning through Planning under Uncertainty", "publication_year": 2025, "publication_date": "2025-10-21", "type": "preprint", "language": null, "authorships": [{"author_position": "first", "author": {"id": null, "display_name": "Deng, Ziwei", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Deng, Ziwei", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Deng, Mian", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Deng, Mian", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5061065428", "display_name": "C. Liang", "orcid": "https://orcid.org/0009-0005-2251-7603", "observed_orcids": ["https://orcid.org/0009-0005-2251-7603", "https://orcid.org/0009-0009-2882-6940"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liang, Chenjing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5065397573", "display_name": "Zeming Gao", "orcid": "https://orcid.org/0000-0002-8117-6467", "observed_orcids": ["https://orcid.org/0000-0002-8117-6467"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Gao, Zeming", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Ma, Chennan", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Ma, Chennan", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5087826819", "display_name": "C. X. Lin", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Lin, Chenxing", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5100758732", "display_name": "Haipeng Zhang", "orcid": "https://orcid.org/0000-0001-5741-2311", "observed_orcids": ["https://orcid.org/0000-0001-5741-2311", "https://orcid.org/0009-0009-4153-984X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Zhang, Haipeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Mei, Songzhu", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Mei, Songzhu", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": null, "display_name": "Shen, Siqi", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Shen, Siqi", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5100417009", "display_name": "Cheng Wang", "orcid": "https://orcid.org/0000-0002-5881-7756", "observed_orcids": ["https://orcid.org/0000-0002-5881-7756"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Wang, Cheng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Large": [0], "Language": [1], "Models": [2], "(LLMs)": [3], "are": [4, 24, 113], "increasingly": [5], "being": [6], "explored": [7], "across": [8], "a": [9, 159, 164], "range": [10], "of": [11, 38, 108, 152, 166, 195, 205], "reasoning": [12, 19, 41, 75, 118, 209], "tasks.": [13], "However,": [14, 80, 111], "LLMs": [15, 39], "sometimes": [16], "struggle": [17], "with": [18, 93, 102, 123, 187], "tasks": [20, 119, 210], "under": [21, 211], "uncertainty": [22, 45, 50, 55, 72, 103, 128, 141, 194], "that": [23, 120, 139], "relatively": [25], "easy": [26], "for": [27, 40, 116], "humans,": [28], "such": [29, 47], "as": [30, 48, 158], "planning": [31, 137], "actions": [32], "in": [33, 91, 129, 155, 207], "stochastic": [34, 59, 94], "environments.": [35], "The": [36], "adoption": [37], "is": [42], "impeded": [43], "by": [44, 104], "challenges,": [46], "LLM": [49, 54, 71, 130], "and": [51, 176], "environmental": [52, 84], "uncertainty.": [53, 212], "arises": [56], "from": [57], "the": [58, 106, 124, 150, 156, 170, 193, 203], "sampling": [60], "process": [61], "inherent": [62], "to": [63, 88, 168], "LLMs.": [64], "Most": [65], "LLM-based": [66, 136, 208], "Decision-Making": [67], "(LDM)": [68], "approaches": [69, 82, 100], "address": [70, 127], "through": [73], "multiple": [74], "chains": [76], "or": [77], "search": [78], "trees.": [79], "these": [81], "overlook": [83], "uncertainty,": [85], "which": [86, 162, 191], "leads": [87], "poor": [89], "performance": [90], "environments": [92], "state": [95], "transitions.": [96], "Some": [97], "recent": [98], "LDM": [99], "deal": [101], "forecasting": [105], "probability": [107], "unknown": [109], "variables.": [110], "they": [112], "not": [114], "designed": [115], "multi-step": [117], "require": [121], "interaction": [122], "environment.": [125], "To": [126, 173], "decision-making,": [131], "we": [132, 201], "introduce": [133], "PlanU,": [134], "an": [135, 183], "method": [138], "captures": [140], "within": [142], "Monte": [143], "Carlo": [144], "Tree": [145], "Search": [146], "(MCTS).": [147], "PlanU": [148, 181, 206], "models": [149], "return": [151, 171], "each": [153], "node": [154], "MCTS": [157, 196], "quantile": [160], "distribution,": [161], "uses": [163], "set": [165], "quantiles": [167], "represent": [169], "distribution.": [172], "balance": [174], "exploration": [175], "exploitation": [177], "during": [178], "tree": [179], "search,": [180], "introduces": [182], "Upper": [184], "Confidence": [185], "Bounds": [186], "Curiosity": [188], "(UCC)": [189], "score": [190], "estimates": [192], "nodes.": [197], "Through": [198], "extensive": [199], "experiments,": [200], "demonstrate": [202], "effectiveness": [204]}, "primary_topic": {"id": "https://openalex.org/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.9496999979019165, "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/T10906", "display_name": "AI-based Problem Solving and Planning", "score": 0.9496999979019165, "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/T11574", "display_name": "Artificial Intelligence in Games", "score": 0.02979999966919422, "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": 0.0038999998942017555, "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:2510.18442", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2510.18442", "pdf_url": "https://arxiv.org/pdf/2510.18442", "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/W4409051423", "doi": "https://doi.org/10.48550/arxiv.2503.20271", "title": "ViLBench: A Suite for Vision-Language Process Reward Modeling", "publication_year": 2025, "publication_date": "2025-03-26", "type": "preprint", "language": "en", "authorships": [{"author_position": "first", "author": {"id": "https://openalex.org/A5048179343", "display_name": "Haoqin Tu", "orcid": "https://orcid.org/0000-0002-5627-249X", "observed_orcids": ["https://orcid.org/0000-0002-5627-249X"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tu, Haoqin", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5072751690", "display_name": "Weitao Feng", "orcid": "https://orcid.org/0000-0003-2517-9206", "observed_orcids": ["https://orcid.org/0000-0003-2517-9206"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Feng, Weitao", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5040253516", "display_name": "Hardy Chen", "orcid": null, "observed_orcids": []}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Chen, Hardy", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5028251167", "display_name": "Hui Liu", "orcid": "https://orcid.org/0000-0002-7887-7537", "observed_orcids": ["https://orcid.org/0000-0002-7887-7537"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Liu, Hui", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "middle", "author": {"id": "https://openalex.org/A5102008510", "display_name": "Xianfeng Tang", "orcid": "https://orcid.org/0000-0003-1554-2761", "observed_orcids": ["https://orcid.org/0000-0003-1554-2761"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Tang, Xianfeng", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}, {"author_position": "last", "author": {"id": "https://openalex.org/A5022344556", "display_name": "Cihang Xie", "orcid": "https://orcid.org/0000-0003-1243-8045", "observed_orcids": ["https://orcid.org/0000-0003-1243-8045"]}, "institutions": [], "countries": [], "is_corresponding": false, "raw_author_name": "Xie, Cihang", "raw_affiliation_strings": [], "raw_orcid": null, "affiliations": []}], "abstract_inverted_index": {"Process-supervised": [0], "reward": [1, 57, 60, 65, 109, 143, 151], "models": [2, 51, 61, 66, 144], "serve": [3], "as": [4, 53], "a": [5, 101, 132], "fine-grained": [6], "function": [7], "that": [8, 74], "provides": [9], "detailed": [10], "step-wise": [11], "feedback": [12], "to": [13, 105, 163, 175, 178], "model": [14, 160], "responses,": [15], "facilitating": [16], "effective": [17], "selection": [18], "of": [19, 56, 168], "reasoning": [20], "trajectories": [21], "for": [22, 125], "complex": [23], "tasks.": [24], "Despite": [25], "its": [26, 179], "advantages,": [27], "evaluation": [28], "on": [29, 68, 182], "PRMs": [30], "remains": [31], "less": [32], "explored,": [33], "especially": [34], "in": [35], "the": [36, 122, 137, 191], "multimodal": [37], "domain.": [38], "To": [39, 94], "address": [40], "this": [41, 43], "gap,": [42], "paper": [44], "first": [45], "benchmarks": [46], "current": [47, 126], "vision": [48], "large": [49], "language": [50], "(VLLMs)": [52], "two": [54], "types": [55], "models:": [58], "output": [59], "(ORMs)": [62], "and": [63, 84, 142, 173, 199], "process": [64, 108, 150], "(PRMs)": [67], "multiple": [69], "vision-language": [70, 102, 149], "benchmarks,": [71], "which": [72], "reveal": [73], "neither": [75], "ORM": [76], "nor": [77], "PRM": [78], "consistently": [79], "outperforms": [80], "across": [81], "all": [82], "tasks,": [83], "superior": [85], "VLLMs": [86, 141], "do": [87], "not": [88], "necessarily": [89], "yield": [90], "better": [91], "rewarding": [92], "performance.": [93], "further": [95], "advance": [96], "evaluation,": [97], "we": [98, 129], "introduce": [99], "ViLBench,": [100], "benchmark": [103], "designed": [104], "require": [106], "intensive": [107], "signals.": [110], "Notably,": [111], "OpenAI's": [112], "GPT-4o": [113], "with": [114, 195], "Chain-of-Thought": [115], "(CoT)": [116], "achieves": [117], "only": [118], "27.3%": [119], "accuracy,": [120], "indicating": [121], "benchmark's": [123], "challenge": [124], "VLLMs.": [127], "Lastly,": [128], "preliminarily": [130], "showcase": [131], "promising": [133], "pathway": [134], "towards": [135], "bridging": [136], "gap": [138], "between": [139], "general": [140], "--": [145], "by": [146, 184], "collecting": [147], "73.6K": [148], "data": [152], "using": [153], "an": [154, 165], "enhanced": [155], "tree-search": [156], "algorithm,": [157], "our": [158, 196], "3B": [159], "is": [161], "able": [162], "achieve": [164], "average": [166], "improvement": [167], "3.3%": [169], "over": [170], "standard": [171], "CoT": [172], "up": [174], "2.5%": [176], "compared": [177], "untrained": [180], "counterpart": [181], "ViLBench": [183], "selecting": [185], "OpenAI": [186], "o1's": [187], "generations.": [188], "We": [189], "release": [190], "implementations": [192], "at": [193], "https://ucsc-vlaa.github.io/ViLBench": [194], "code,": [197], "model,": [198], "data.": [200]}, "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/T10028", "display_name": "Topic Modeling", "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"}}, {"id": "https://openalex.org/T10181", "display_name": "Natural Language Processing Techniques", "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:2503.20271", "is_oa": true, "landing_page_url": "http://arxiv.org/abs/2503.20271", "pdf_url": "https://arxiv.org/pdf/2503.20271", "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}], "group_by": []}