{"id":"https://openalex.org/W4416034425","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1367","title":"Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems","display_name":"Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034425","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1367"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1367","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1367","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1367.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1367.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012625793","display_name":"Aakriti Agrawal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aakriti Agrawal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060415215","display_name":"Rohith Aralikatti","orcid":"https://orcid.org/0000-0002-6857-6896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohith Aralikatti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109022197","display_name":"Anirudh Satheesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirudh Satheesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052013511","display_name":"Souradip Chakraborty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Souradip Chakraborty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039563144","display_name":"Amrit Singh Bedi","orcid":"https://orcid.org/0000-0002-8807-2695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amrit Singh Bedi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037162168","display_name":"Furong Huang","orcid":"https://orcid.org/0000-0002-7393-1047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furong Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15492011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25090","last_page":"25098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.48010000586509705,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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":0.48010000586509705,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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":0.16419999301433563,"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/T12031","display_name":"Speech and dialogue systems","score":0.05460000038146973,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.27300000190734863},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.27149999141693115},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.2614000141620636},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.24549999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407000184059143},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.24549999833106995},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2401999980211258},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23720000684261322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1367","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1367","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1367.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.1367","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1367","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1367.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":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5702281522","display_name":"FAI: Toward Fair Decision Making and Resource Allocation with Application to AI-Assisted Graduate Admission and Degree Completion","funder_award_id":"2147276","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8945643642","display_name":"Institute for Trustworthy AI in Law and Society (TRAILS)","funder_award_id":"2229885","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034425.pdf","grobid_xml":"https://content.openalex.org/works/W4416034425.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,55],"demonstrated":[5],"exceptional":[6],"capabilities,":[7],"yet":[8],"selecting":[9],"the":[10,76,90],"most":[11],"reliable":[12],"response":[13,78],"from":[14,40,79],"multiple":[15,38,80,116],"LLMs":[16,82],"remains":[17],"a":[18,41,67,84],"challenge,":[19],"particularly":[20],"in":[21],"resourceconstrained":[22],"settings.Existing":[23],"approaches":[24],"often":[25,59],"depend":[26],"on":[27,119],"costly":[28],"external":[29],"verifiers,":[30],"human":[31],"evaluators,":[32],"or":[33],"self-consistency":[34],"techniques":[35],"that":[36],"require":[37],"samples":[39],"single":[42,51,63],"model.While":[43],"multi-LLM":[44],"systems":[45],"produce":[46],"more":[47],"diverse":[48],"responses":[49],"than":[50],"models":[52],"and":[53,70,93,104,112,124],"thus":[54],"greater":[56],"potential,":[57],"they":[58],"underperform":[60],"compared":[61],"to":[62,74],"LLM":[64,110],"self-consistency.We":[65],"propose":[66],"principled,":[68],"novel":[69],"computationally":[71],"efficient":[72],"method":[73,98],"select":[75],"best":[77],"different":[81],"using":[83],"calibrated":[85],"log-likelihood":[86],"score,":[87],"implicitly":[88],"leveraging":[89],"inherent":[91],"knowledge":[92],"confidence":[94],"of":[95,101],"these":[96],"models.Our":[97],"demonstrates":[99],"improvements":[100],"approx.4%,":[102],"3%,":[103],"5%":[105],"across":[106],"both":[107],"debate":[108],"(multi-round":[109],"discussions)":[111],"non-debate":[113],"(Best-of-N":[114],"with":[115],"LLMs)":[117],"settings":[118],"GSM8K,":[120],"MMLU":[121],"(6":[122],"subsets),":[123],"ARC":[125],"datasets":[126],"respectively":[127],"1":[128],".":[129]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-11-08T00:00:00"}