{"id":"https://openalex.org/W4404782622","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.443","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","display_name":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782622","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.443"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.443","pdf_url":"https://aclanthology.org/2024.emnlp-main.443.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.443.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037714222","display_name":"Gal Yona","orcid":null},"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":true,"raw_author_name":"Gal Yona","raw_affiliation_strings":["Google Research Google Research Tel Aviv University , Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research Google Research Tel Aviv University , Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027223654","display_name":"Roee Aharoni","orcid":null},"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":"Roee Aharoni","raw_affiliation_strings":["Google Research Google Research Tel Aviv University , Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research Google Research Tel Aviv University , Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065717258","display_name":"Mor Geva","orcid":"https://orcid.org/0000-0001-9529-6315"},"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":"Mor Geva","raw_affiliation_strings":["Google Research Google Research Tel Aviv University , Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research Google Research Tel Aviv University , Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037714222"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.9072,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92285433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7752","last_page":"7764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8004999756813049,"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":0.8004999756813049,"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/computer-science","display_name":"Computer science","score":0.7255178093910217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5144286751747131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4199759364128113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7255178093910217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5144286751747131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4199759364128113}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.443","pdf_url":"https://aclanthology.org/2024.emnlp-main.443.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.443","pdf_url":"https://aclanthology.org/2024.emnlp-main.443.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782622.pdf","grobid_xml":"https://content.openalex.org/works/W4404782622.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/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"posit":[1],"that":[2,117,128],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"should":[7,38],"be":[8],"capable":[9],"of":[10,100],"expressing":[11],"their":[12,125,135],"intrinsic":[13,64],"uncertainty":[14,41,56,106],"in":[15,66],"natural":[16],"language.For":[17],"example,":[18],"if":[19],"the":[20,31,59,62,67,72,84],"LLM":[21],"is":[22,131],"equally":[23],"likely":[24],"to":[25,30,133],"output":[26],"two":[27],"contradicting":[28],"answers":[29],"same":[32],"question,":[33],"then":[34],"its":[35,44,87],"generated":[36],"response":[37,55],"reflect":[39],"this":[40],"by":[42,74],"hedging":[43],"answer":[45],"(e.g.,":[46],"\"I'm":[47],"not":[48],"sure,":[49],"but":[50],"I":[51],"think...\").We":[52],"formalize":[53],"faithful":[54],"based":[57],"on":[58,107],"gap":[60],"between":[61],"model's":[63],"confidence":[65],"assertions":[68],"it":[69,90],"makes":[70],"and":[71,94,127],"decisiveness":[73],"which":[75],"they":[76],"are":[77,120],"conveyed.This":[78],"example-level":[79],"metric":[80],"reliably":[81],"indicates":[82],"whether":[83],"model":[85],"reflects":[86],"uncertainty,":[88,126],"as":[89],"penalizes":[91],"both":[92],"excessive":[93],"insufficient":[95],"hedging.We":[96],"evaluate":[97],"a":[98],"variety":[99],"aligned":[101],"LLMs":[102,119],"at":[103,122],"faithfully":[104,123],"communicating":[105],"several":[108],"knowledgeintensive":[109],"question":[110],"answering":[111],"tasks.Our":[112],"results":[113],"provide":[114],"strong":[115],"evidence":[116],"modern":[118],"poor":[121],"conveying":[124],"better":[129],"alignment":[130],"necessary":[132],"improve":[134],"trustworthiness.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}