{"id":"https://openalex.org/W7166832105","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1280","title":"Confidence Estimation for LLMs in Multi-turn Interactions","display_name":"Confidence Estimation for LLMs in Multi-turn Interactions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166832105","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1280"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1280","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1280","pdf_url":"https://aclanthology.org/2026.findings-acl.1280.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1280.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139796025","display_name":"Caiqi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiqi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085270850","display_name":"Ruihan Yang","orcid":"https://orcid.org/0000-0003-3154-4150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruihan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730206","display_name":"Xiaochen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaochen Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139772637","display_name":"Chengzu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengzu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727741","display_name":"Tiancheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiancheng Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008492181","display_name":"Yijiang River Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijiang River Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139743713","display_name":"Deqing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deqing Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139736903","display_name":"Nigel Collier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nigel Collier","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86378066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25661","last_page":"25676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11720","display_name":"Probability and Risk Models","score":0.027499999850988388,"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"}},"topics":[{"id":"https://openalex.org/T11720","display_name":"Probability and Risk Models","score":0.027499999850988388,"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/T10974","display_name":"Advanced Queuing Theory Analysis","score":0.02449999935925007,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"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/T10044","display_name":"Protein Structure and Dynamics","score":0.021800000220537186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6237999796867371},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.3896999955177307},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.24809999763965607},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.24369999766349792}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4239000082015991},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32440000772476196},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.27399998903274536},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.24809999763965607},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.24469999969005585},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.24369999766349792},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.24009999632835388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1280","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1280","pdf_url":"https://aclanthology.org/2026.findings-acl.1280.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1280","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1280","pdf_url":"https://aclanthology.org/2026.findings-acl.1280.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166832105.pdf","grobid_xml":"https://content.openalex.org/works/W7166832105.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"confidence":[1,25,40,65,85,118],"estimation":[2,41,66],"is":[3,34,45],"a":[4,71,98,105,130,147],"promising":[5],"direction":[6],"for":[7,47,109,150],"mitigating":[8],"hallucinations":[9],"in":[10,26,42,67,76,125,165],"Large":[11],"Language":[12],"Models":[13],"(LLMs),":[14],"current":[15],"research":[16],"dominantly":[17],"focuses":[18],"on":[19],"single-turn":[20],"settings.The":[21],"dynamics":[22],"of":[23,64,84],"model":[24],"multi-turn":[27,43,68],"conversations,":[28],"where":[29],"context":[30],"accumulates":[31],"and":[32,55,82,104,123,154,160],"ambiguity":[33],"progressively":[35],"resolved,":[36],"remain":[37],"largely":[38],"unexplored.Reliable":[39],"settings":[44],"critical":[46],"many":[48],"downstream":[49],"applications,":[50],"such":[51],"as":[52,86],"autonomous":[53],"agents":[54],"human-in-the-loop":[56],"systems.This":[57],"work":[58,145],"presents":[59],"the":[60,139],"first":[61],"systematic":[62],"study":[63],"interactions,":[69],"establishing":[70],"formal":[72],"evaluation":[73,112],"framework":[74],"grounded":[75],"two":[77],"key":[78],"desiderata:":[79],"per-turn":[80],"calibration":[81,122],"monotonicity":[83,124],"more":[87,152],"information":[88],"becomes":[89],"available.To":[90],"facilitate":[91],"this,":[92],"we":[93],"introduce":[94],"novel":[95],"metrics,":[96],"including":[97],"length-normalized":[99],"Expected":[100],"Calibration":[101],"Error":[102],"(InfoECE),":[103],"new":[106],"\"Hinter-Guesser\"":[107],"paradigm":[108],"generating":[110],"controlled":[111],"datasets.Our":[113],"experiments":[114],"reveal":[115],"that":[116,133],"widely-used":[117],"techniques":[119],"struggle":[120],"with":[121],"multiturn":[126],"dialogues.We":[127],"propose":[128],"P(SUFFICIENT),":[129],"logit-based":[131],"probe":[132],"achieves":[134],"comparatively":[135],"better":[136],"performance,":[137],"although":[138],"task":[140],"remains":[141],"far":[142],"from":[143],"solved.Our":[144],"provides":[146],"foundational":[148],"methodology":[149],"developing":[151],"reliable":[153],"trustworthy":[155],"conversational":[156],"agents.*":[157],"Equal":[158],"contribution.Codes":[159],"data":[161],"can":[162],"be":[163],"found":[164],"GitHub.":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}