{"id":"https://openalex.org/W7167929364","doi":"https://doi.org/10.1145/3805712.3809846","title":"Calibrating Uncertainty with Cross-Model Consistency for LLM Hallucination Mitigation","display_name":"Calibrating Uncertainty with Cross-Model Consistency for LLM Hallucination Mitigation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167929364","doi":"https://doi.org/10.1145/3805712.3809846"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809846","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140391477","display_name":"Shu Zhou","orcid":"https://orcid.org/0000-0001-5935-3159"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Zhou","raw_affiliation_strings":["School of Information Management, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5935-3159","affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103607985","display_name":"Rui Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ling","raw_affiliation_strings":["School of Information Management, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0000-6734-560X","affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140401006","display_name":"Junan Chen","orcid":"https://orcid.org/0009-0009-4646-4875"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junan Chen","raw_affiliation_strings":["School of Information Management, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-4646-4875","affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080986966","display_name":"Tao Fan","orcid":"https://orcid.org/0000-0002-6846-2901"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Fan","raw_affiliation_strings":["Nanjing University of Finance and Economics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6846-2901","affiliations":[{"raw_affiliation_string":"Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100599811","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-0131-0823"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Information Management, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0131-0823","affiliations":[{"raw_affiliation_string":"School of Information Management, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"4385","last_page":"4390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3034999966621399,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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":0.3034999966621399,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"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/T11147","display_name":"Misinformation and Its Impacts","score":0.2761000096797943,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.05130000039935112,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7797999978065491},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7608000040054321},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5493000149726868},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.43650001287460327},{"id":"https://openalex.org/keywords/measurement-uncertainty","display_name":"Measurement uncertainty","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7797999978065491},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7608000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685999989509583},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C122377713","wikidata":"https://www.wikidata.org/wiki/Q4422799","display_name":"Weak consistency","level":4,"score":0.2897999882698059},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2963339397","https://openalex.org/W3024308166","https://openalex.org/W3201174429","https://openalex.org/W4385571189","https://openalex.org/W4402683996","https://openalex.org/W4404782206","https://openalex.org/W4410638155","https://openalex.org/W4411630296","https://openalex.org/W4412944639","https://openalex.org/W7106263165"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,59],"known":[5],"to":[6,21,63],"hallucinate,":[7],"generating":[8],"non-factual":[9],"outputs":[10],"that":[11,52,84,134],"undermine":[12],"user":[13],"trust.":[14],"Recent":[15],"ensemble-based":[16],"approaches":[17],"leverage":[18],"uncertainty":[19,39,105,110],"estimation":[20],"select":[22],"among":[23],"multiple":[24,57,94],"LLM":[25],"responses,":[26],"achieving":[27],"promising":[28],"results":[29],"in":[30,151],"hallucination":[31,139],"mitigation.":[32],"However,":[33],"these":[34],"methods":[35],"treat":[36],"each":[37],"model's":[38],"independently,":[40],"overlooking":[41],"a":[42,82],"crucial":[43],"signal:":[44],"cross-model":[45,90],"consistency.":[46],"In":[47],"this":[48,74],"work,":[49],"we":[50,76],"observe":[51],"answers":[53,108],"agreed":[54],"upon":[55],"by":[56,149,159],"models":[58,95],"significantly":[60],"more":[61,117],"likely":[62],"be":[64],"correct-a":[65],"manifestation":[66],"of":[67,70],"the":[68,98,103,143],"\"wisdom":[69],"crowds\"":[71],"principle.":[72],"Leveraging":[73],"insight,":[75],"propose":[77],"Consistency-Calibrated":[78],"Uncertainty":[79],"Fusion":[80],"(CCUF),":[81],"framework":[83],"calibrates":[85],"individual":[86],"model":[87],"uncertainties":[88],"using":[89],"consistency":[91],"scores.":[92],"When":[93],"converge":[96],"on":[97,127,157],"same":[99],"answer,":[100],"CCUF":[101,135],"reduces":[102],"associated":[104],"estimate;":[106],"when":[107],"diverge,":[109],"remains":[111],"elevated.":[112],"This":[113],"calibration":[114],"mechanism":[115],"enables":[116],"reliable":[118],"answer":[119],"selection":[120],"for":[121],"factoid":[122],"question":[123],"answering.":[124],"Extensive":[125],"experiments":[126],"TruthfulQA,":[128],"TriviaQA,":[129],"and":[130],"FACTOR-news":[131],"benchmarks":[132],"demonstrate":[133],"consistently":[136],"outperforms":[137],"state-of-the-art":[138],"mitigation":[140],"methods,":[141],"surpassing":[142],"previous":[144],"best":[145],"ensemble":[146],"method":[147],"UAF":[148],"3.4%":[150],"accuracy":[152],"while":[153],"exceeding":[154],"GPT-4":[155],"performance":[156],"TruthfulQA":[158],"5.2%.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}