{"id":"https://openalex.org/W7133313204","doi":"https://doi.org/10.48550/arxiv.2603.00105","title":"LIDS: LLM Summary Inference Under the Layered Lens","display_name":"LIDS: LLM Summary Inference Under the Layered Lens","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7133313204","doi":"https://doi.org/10.48550/arxiv.2603.00105"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00105","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127876731","display_name":"Dylan Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Dylan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139819900","display_name":"Yingying Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Yingying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034015361","display_name":"Jinchi Lv","orcid":"https://orcid.org/0000-0002-5881-9591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Jinchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.24809999763965607,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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":0.24809999763965607,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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":0.2142000049352646,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05299999937415123,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6829000115394592},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6442999839782715},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5388000011444092},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48489999771118164},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42480000853538513},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4171999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40709999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109000086784363},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6442999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5899999737739563},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46230000257492065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3968999981880188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C11192451","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Stylometry","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00105","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00105","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.8080800771713257,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,15],"models":[2],"(LLMs)":[3],"have":[4],"gained":[5],"significant":[6],"attention":[7],"by":[8],"many":[9],"researchers":[10],"and":[11,73,104,111,164,171],"practitioners":[12],"in":[13,23,57,148],"natural":[14,125],"processing":[16],"(NLP)":[17],"since":[18],"the":[19,41,50,78,99,102,108,116,149,161],"introduction":[20],"of":[21,28,43,52,65,127,166,180],"ChatGPT":[22,29],"2022.":[24],"One":[25],"notable":[26],"feature":[27],"is":[30],"its":[31],"ability":[32],"to":[33,49,97,114,138,173],"generate":[34],"summaries":[35,45,103],"based":[36],"on":[37],"prompts.":[38],"Yet":[39],"evaluating":[40],"quality":[42],"these":[44],"remains":[46],"challenging":[47],"due":[48],"complexity":[51],"language.":[53],"To":[54],"this":[55,58],"end,":[56],"paper":[59],"we":[60],"suggest":[61],"a":[62,92,120,124,178],"new":[63],"method":[64],"LLM":[66],"summary":[67,79,129,150],"inference":[68],"with":[69,82,144,151],"BERT-SVD-based":[70],"direction":[71,95],"metric":[72,96],"SOFARI":[74,137],"(LIDS)":[75],"that":[76],"assesses":[77],"accuracy":[80],"equipped":[81],"interpretable":[83],"key":[84,141],"words":[85,142],"for":[86,130],"layered":[87],"themes.":[88],"The":[89],"LIDS":[90,122,167],"uses":[91],"latent":[93,146],"SVD-based":[94],"measure":[98],"similarity":[100,175],"between":[101],"original":[105],"text,":[106],"leveraging":[107],"BERT":[109],"embeddings":[110],"repeated":[112],"prompts":[113],"quantify":[115],"statistical":[117],"uncertainty.":[118],"As":[119],"result,":[121],"gives":[123],"embedding":[126],"each":[128,145],"large":[131],"text":[132],"reduction.":[133],"We":[134],"further":[135],"exploit":[136],"uncover":[139],"important":[140],"associated":[143],"theme":[147],"controlled":[152],"false":[153],"discovery":[154],"rate":[155],"(FDR).":[156],"Comprehensive":[157],"empirical":[158],"studies":[159],"demonstrate":[160],"practical":[162],"utility":[163],"robustness":[165],"through":[168],"human":[169],"verification":[170],"comparisons":[172],"other":[174],"metrics,":[176],"including":[177],"comparison":[179],"different":[181],"LLMs.":[182]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-03-04T00:00:00"}