{"id":"https://openalex.org/W4416034332","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.841","title":"Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?","display_name":"Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034332","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.841"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.841","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.841","pdf_url":"https://aclanthology.org/2025.findings-emnlp.841.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.841.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308551","display_name":"Yang Nan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308552","display_name":"Pengfei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308553","display_name":"Ravi Tandon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravi Tandon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120308554","display_name":"Han Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Xu","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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15551","last_page":"15569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13309","display_name":"Reliability and Agreement in Measurement","score":0.1388999968767166,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13309","display_name":"Reliability and Agreement in Measurement","score":0.1388999968767166,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.09440000355243683,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10206","display_name":"Meta-analysis and systematic reviews","score":0.0406000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.26649999618530273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.25609999895095825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24729999899864197},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.22840000689029694},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.21799999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41990000009536743},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24729999899864197},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.22840000689029694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.21799999475479126},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.21660000085830688},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.20669999718666077},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.20520000159740448}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.841","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.841","pdf_url":"https://aclanthology.org/2025.findings-emnlp.841.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.841","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.841","pdf_url":"https://aclanthology.org/2025.findings-emnlp.841.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034332.pdf","grobid_xml":"https://content.openalex.org/works/W4416034332.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"delivered":[5],"significant":[6],"breakthroughs":[7],"across":[8],"diverse":[9],"domains":[10],"but":[11],"can":[12],"still":[13],"produce":[14],"unreliable":[15],"or":[16,123,138],"misleading":[17],"outputs,":[18],"posing":[19],"critical":[20],"challenges":[21],"for":[22,167],"real-world":[23],"applications.While":[24],"many":[25],"recent":[26],"studies":[27],"focus":[28],"on":[29,150],"quantifying":[30],"model":[31,96,131],"uncertainty,":[32,106],"relatively":[33],"little":[34],"work":[35],"has":[36],"been":[37],"devoted":[38],"to":[39,89,99,141],"diagnosing":[40,159],"the":[41,55,68,102,115,129,134,142,165],"source":[42,104],"of":[43,57,71,93,105,120],"uncertainty.In":[44,143],"this":[45,74],"study,":[46],"we":[47,76,146],"show":[48],"that,":[49],"when":[50],"an":[51,86],"LLM":[52,83,88,173],"is":[53,97],"uncertain,":[54],"patterns":[56,92],"disagreement":[58],"among":[59],"its":[60,156],"multiple":[61,78],"generated":[62],"responses":[63,79],"contain":[64],"rich":[65],"clues":[66],"about":[67,101],"underlying":[69],"cause":[70],"uncertainty.To":[72],"illustrate":[73],"point,":[75],"collect":[77],"from":[80,112],"a":[81,118],"target":[82],"and":[84,153,175],"employ":[85],"auxiliary":[87,95,130],"analyze":[90],"their":[91],"disagreement.The":[94],"tasked":[98],"reason":[100],"likely":[103],"such":[107],"as":[108],"whether":[109],"it":[110],"stems":[111],"ambiguity":[113],"in":[114,158],"input":[116],"question,":[117],"lack":[119],"relevant":[121,168],"knowledge,":[122],"both.In":[124],"cases":[125],"involving":[126],"knowledge":[127],"gaps,":[128],"also":[132],"identifies":[133],"specific":[135],"missing":[136],"facts":[137],"concepts":[139],"contributing":[140],"our":[144,148],"experiment,":[145],"validate":[147],"framework":[149],"Am-bigQA,":[151],"OpenBookQA,":[152],"MMLU-Pro,":[154],"confirming":[155],"generality":[157],"distinct":[160],"uncertainty":[161],"sources.Such":[162],"diagnosis":[163],"shows":[164],"potential":[166],"manual":[169],"interventions":[170],"that":[171],"improve":[172],"performance":[174],"reliability.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}