{"id":"https://openalex.org/W4412944528","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1316","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","display_name":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944528","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1316"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1316","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1316","pdf_url":"https://aclanthology.org/2025.findings-acl.1316.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 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-acl.1316.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046651998","display_name":"Cuiping Xu","orcid":"https://orcid.org/0000-0002-2857-540X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenjun Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204273","display_name":"Bingbing Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingbing Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102741786","display_name":"Bin Han","orcid":"https://orcid.org/0000-0002-5280-9456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033282902","display_name":"Robert E. Wolfe","orcid":"https://orcid.org/0000-0002-0915-1855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Wolfe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lucy Lu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucy Lu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007124763","display_name":"Bill Howe","orcid":"https://orcid.org/0000-0001-8588-8472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bill Howe","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25655","last_page":"25672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9448999762535095,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9448999762535095,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.9582474231719971},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.44095608592033386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40301835536956787},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.38001227378845215},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.28644537925720215}],"concepts":[{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.9582474231719971},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44095608592033386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40301835536956787},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38001227378845215},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28644537925720215}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1316","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1316","pdf_url":"https://aclanthology.org/2025.findings-acl.1316.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1316","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1316","pdf_url":"https://aclanthology.org/2025.findings-acl.1316.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317052","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944528.pdf","grobid_xml":"https://content.openalex.org/works/W4412944528.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4253467046","https://openalex.org/W4251085376","https://openalex.org/W2066240519","https://openalex.org/W2775388773","https://openalex.org/W2991634017","https://openalex.org/W4246334359","https://openalex.org/W2098014671"],"abstract_inverted_index":{"Psychology":[0],"research":[1],"has":[2],"shown":[3],"that":[4,43,116,146],"humans":[5],"are":[6],"poor":[7],"at":[8],"estimating":[9],"their":[10,86],"performance":[11],"on":[12,17,22,32,64,93,127,135],"tasks,":[13],"tending":[14],"towards":[15],"underconfidence":[16],"easy":[18],"tasks":[19,37,150],"and":[20,30,41,58,74,106,138,143,154],"overconfidence":[21,153],"difficult":[23],"tasks.We":[24],"examine":[25],"three":[26],"LLMs,":[27],"Llama-3-70B-instruct,":[28],"Claude-3-Sonnet,":[29],"GPT-4o,":[31],"a":[33,113],"range":[34],"of":[35,38,51,120,149],"QA":[36],"varying":[39],"difficulty,":[40,57],"show":[42,145],"models":[44,76],"exhibit":[45],"subtle":[46],"differences":[47],"from":[48],"human":[49],"patterns":[50],"overconfidence:":[52],"less":[53],"sensitive":[54],"to":[55,61,102,159],"task":[56,160],"when":[59],"prompted":[60],"answer":[62,88],"based":[63],"different":[65,71],"personas-e.g.,":[66],"expert":[67],"vs":[68],"layman,":[69],"or":[70],"race,":[72],"gender,":[73],"ages-the":[75],"will":[77],"respond":[78],"with":[79],"stereotypically":[80],"biased":[81],"confidence":[82,104,125],"estimations":[83],"even":[84],"though":[85],"underlying":[87],"accuracy":[89],"remains":[90],"the":[91,133,136],"same.Based":[92],"these":[94,110],"observations,":[95],"we":[96],"propose":[97],"Answer-Free":[98],"Confidence":[99],"Estimation":[100],"(AFCE)":[101],"improve":[103],"calibration":[105],"LLM":[107],"interpretability":[108],"in":[109],"settings.AFCE":[111],"is":[112],"self-assessment":[114],"method":[115],"employs":[117],"two":[118],"stages":[119],"prompting,":[121],"first":[122],"eliciting":[123],"only":[124],"scores":[126],"questions,":[128],"then":[129],"asking":[130],"separately":[131],"for":[132],"answer.Experiments":[134],"MMLU":[137],"GPQA":[139],"datasets":[140],"spanning":[141],"subjects":[142],"difficulty":[144],"this":[147],"separation":[148],"significantly":[151],"reduces":[152],"delivers":[155],"more":[156],"human-like":[157],"sensitivity":[158],"difficulty.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}