{"id":"https://openalex.org/W4388717366","doi":"https://doi.org/10.48550/arxiv.2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","display_name":"A Survey of Confidence Estimation and Calibration in Large Language Models","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4388717366","doi":"https://doi.org/10.48550/arxiv.2311.08298"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.08298","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.08298","pdf_url":"https://arxiv.org/pdf/2311.08298","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,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.08298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073054282","display_name":"Jiahui Geng","orcid":"https://orcid.org/0000-0002-4205-8230","observed_orcids":["https://orcid.org/0000-0002-4205-8230"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Jiahui","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067158103","display_name":"Fengyu Cai","orcid":"https://orcid.org/0009-0009-7943-439X","observed_orcids":["https://orcid.org/0009-0009-7943-439X"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cai, Fengyu","raw_affiliation_strings":["Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631225","display_name":"Yuxia Wang","orcid":"https://orcid.org/0000-0002-6095-1030","observed_orcids":["https://orcid.org/0000-0002-6095-1030"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxia","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070544702","display_name":"Heinz Koeppl","orcid":"https://orcid.org/0000-0002-8305-9379","observed_orcids":["https://orcid.org/0000-0002-8305-9379"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Koeppl, Heinz","raw_affiliation_strings":["Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510","observed_orcids":["https://orcid.org/0000-0002-3600-1510"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nakov, Preslav","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621","observed_orcids":["https://orcid.org/0000-0003-2187-7621"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gurevych, Iryna","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.5756999850273132,"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":0.5756999850273132,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.23389999568462372,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.13750000298023224,"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/large-language-models","display_name":"large language models","score":0.9679999947547913},{"id":"https://openalex.org/keywords/confidence-estimation","display_name":"confidence estimation","score":0.9819999933242798},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.7850000262260437},{"id":"https://openalex.org/keywords/factual-errors","display_name":"factual errors","score":0.8489999771118164},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.6000000238418579},{"id":"https://openalex.org/keywords/factual-reliability","display_name":"factual reliability","score":0.41999998688697815},{"id":"https://openalex.org/keywords/risk-reduction","display_name":"risk mitigation","score":0.3019999861717224}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6208131313323975},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5623825788497925},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5502128005027771},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4862876832485199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44150885939598083},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3937070965766907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27925246953964233},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14502358436584473},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.08298","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.08298","pdf_url":"https://arxiv.org/pdf/2311.08298","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,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.08298","doi":"https://doi.org/10.48550/arxiv.2311.08298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.08298","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.08298","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.08298","pdf_url":"https://arxiv.org/pdf/2311.08298","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,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388717366.pdf","grobid_xml":"https://content.openalex.org/works/W4388717366.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414878510","https://openalex.org/W7124671838","https://openalex.org/W6948338298","https://openalex.org/W7162467387","https://openalex.org/W4417506933","https://openalex.org/W4407690020","https://openalex.org/W4412875472","https://openalex.org/W4412887878","https://openalex.org/W7171296507","https://openalex.org/W4409363988"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8,38],"a":[9,55],"wide":[10],"range":[11],"of":[12,57],"tasks":[13,40],"in":[14,29],"various":[15],"domains.":[16],"Despite":[17],"their":[18,30,33,109],"impressive":[19],"performance,":[20],"they":[21],"can":[22,41],"be":[23],"unreliable":[24],"due":[25],"to":[26,48,61,71,84],"factual":[27],"errors":[28],"generations.":[31,51],"Assessing":[32],"confidence":[34,102],"and":[35,45,74,94,104,111],"calibrating":[36],"them":[37],"different":[39],"help":[42],"mitigate":[43],"risks":[44],"enable":[46],"LLMs":[47],"produce":[49],"better":[50],"There":[52],"has":[53,66],"been":[54,67],"lot":[56],"recent":[58,97],"research":[59],"aiming":[60],"address":[62],"this,":[63],"but":[64],"there":[65],"no":[68],"comprehensive":[69],"overview":[70],"organize":[72],"it":[73],"outline":[75,91],"the":[76,92],"main":[77],"lessons":[78],"learned.":[79],"The":[80],"present":[81],"survey":[82],"aims":[83],"bridge":[85],"this":[86],"gap.":[87],"In":[88],"particular,":[89],"we":[90,95],"challenges":[93],"summarize":[96],"technical":[98],"advancements":[99],"for":[100,115],"LLM":[101],"estimation":[103],"calibration.":[105],"We":[106],"further":[107],"discuss":[108],"applications":[110],"suggest":[112],"promising":[113],"directions":[114],"future":[116],"work.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-11-16T00:00:00"}