{"id":"https://openalex.org/W4416035528","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","display_name":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035528","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1505"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1505","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","pdf_url":"https://aclanthology.org/2025.emnlp-main.1505.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.emnlp-main.1505.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107941641","display_name":"G. Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabrielle Kaili-May Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037714222","display_name":"Gal Yona","orcid":"https://orcid.org/0009-0002-8519-8230","observed_orcids":["https://orcid.org/0009-0002-8519-8230"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gal Yona","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077903013","display_name":"Avi Caciularu","orcid":"https://orcid.org/0000-0003-0573-1075","observed_orcids":["https://orcid.org/0000-0003-0573-1075"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avi Caciularu","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026091724","display_name":"Idan Szpektor","orcid":"https://orcid.org/0009-0002-2746-4027","observed_orcids":["https://orcid.org/0009-0002-2746-4027"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Idan Szpektor","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031809940","display_name":"Tim G. J. Rudner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tim G. J. Rudner","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064858748","display_name":"Arman Cohan","orcid":"https://orcid.org/0000-0002-8954-2724","observed_orcids":["https://orcid.org/0000-0002-8954-2724"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arman Cohan","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9483,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77104888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"29600","last_page":"29644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4203999936580658,"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":0.4203999936580658,"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":0.3215000033378601,"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":0.17149999737739563,"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/uncertainty-expression","display_name":"uncertainty expression","score":0.6029999852180481},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.6269999742507935},{"id":"https://openalex.org/keywords/faithfulness","display_name":"faithfulness","score":0.7289999723434448},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8849999904632568},{"id":"https://openalex.org/keywords/metacognition","display_name":"metacognition","score":0.8999999761581421},{"id":"https://openalex.org/keywords/factuality","display_name":"factuality","score":0.36500000953674316},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"trustworthiness","score":0.7039999961853027},{"id":"https://openalex.org/keywords/linguistic-uncertainty","display_name":"linguistic uncertainty","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45500001311302185},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3752000033855438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2856999933719635},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2840999960899353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2711000144481659},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2696000039577484},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1505","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","pdf_url":"https://aclanthology.org/2025.emnlp-main.1505.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.24858","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24858","pdf_url":"https://arxiv.org/pdf/2505.24858","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.24858","doi":"https://doi.org/10.48550/arxiv.2505.24858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.24858","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":"doi:10.18653/v1/2025.emnlp-main.1505","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1505","pdf_url":"https://aclanthology.org/2025.emnlp-main.1505.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2900249791","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2139841","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/F4320310223","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035528.pdf","grobid_xml":"https://content.openalex.org/works/W4416035528.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415270619","https://openalex.org/W4404782622","https://openalex.org/W6929465362","https://openalex.org/W7163426460","https://openalex.org/W4402683791","https://openalex.org/W7055216282","https://openalex.org/W4416763768","https://openalex.org/W4406679533","https://openalex.org/W7106483732","https://openalex.org/W4405035947"],"abstract_inverted_index":{"A":[0],"critical":[1,98],"component":[2],"in":[3,130],"the":[4,29],"trustworthiness":[5],"of":[6,33,37,46,58],"LLMs":[7,13,67],"is":[8],"reliable":[9],"uncertainty":[10,47],"communication,":[11],"yet":[12],"often":[14],"use":[15,43],"assertive":[16],"language":[17],"when":[18],"conveying":[19],"false":[20],"claims,":[21],"leading":[22],"to":[23,42,127],"over-reliance":[24],"and":[25,61,73,86,122,132],"eroded":[26],"trust.We":[27],"present":[28],"first":[30],"systematic":[31],"study":[32],"faithful":[34,94,117],"confidence":[35],"calibration":[36,89,106,118],"LLMs,":[38],"benchmarking":[39],"models'":[40],"ability":[41],"linguistic":[44],"expressions":[45],"that":[48,66,74,113],"faithfully":[49],"reflect":[50],"their":[51],"intrinsic":[52],"uncertainty,":[53],"across":[54,119],"a":[55,103],"comprehensive":[56],"array":[57],"models,":[59],"datasets,":[60],"prompting":[62],"strategies.Our":[63],"results":[64],"demonstrate":[65],"largely":[68],"fail":[69],"at":[70],"this":[71,97],"task,":[72],"existing":[75],"interventions":[76],"are":[77],"insufficient:":[78],"standard":[79],"prompt":[80],"approaches":[81],"provide":[82],"only":[83],"marginal":[84],"gains,":[85],"existing,":[87],"factuality-based":[88],"techniques":[90],"can":[91],"even":[92],"harm":[93],"calibration.To":[95],"address":[96],"gap,":[99],"we":[100],"introduce":[101],"MetaFaith,":[102],"novel":[104],"prompt-based":[105],"approach":[107],"inspired":[108],"by":[109,143],"human":[110],"metacognition.We":[111],"show":[112],"MetaFaith":[114],"robustly":[115],"improves":[116],"diverse":[120],"models":[121],"task":[123],"domains,":[124],"enabling":[125],"up":[126],"61%":[128],"improvement":[129],"faithfulness":[131],"achieving":[133],"an":[134],"83%":[135],"win":[136],"rate":[137],"over":[138],"original":[139],"generations":[140],"as":[141],"judged":[142],"humans.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-11-08T00:00:00"}