{"id":"https://openalex.org/W7126447459","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.62","title":"Do Language Models Know When They\u2019re Hallucinating References?","display_name":"Do Language Models Know When They\u2019re Hallucinating References?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126447459","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.62"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.62","pdf_url":"https://aclanthology.org/2024.findings-eacl.62.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.62.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124499962","display_name":"Ayush Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ayush Agrawal","raw_affiliation_strings":["Microsoft Research Stanford University Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Stanford University Microsoft Research","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093650414","display_name":"Mirac Suzgun","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mirac Suzgun","raw_affiliation_strings":["Microsoft Research Stanford University Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Stanford University Microsoft Research","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124495616","display_name":"Lester Mackey","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lester Mackey","raw_affiliation_strings":["Microsoft Research Stanford University Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Stanford University Microsoft Research","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Adam Kalai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Kalai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4209,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89285279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"912","last_page":"928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.20190000534057617,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.20190000534057617,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.031700000166893005,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.03009999915957451,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/hallucinating","display_name":"Hallucinating","score":0.6693000197410583},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.33340001106262207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.326200008392334},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3190000057220459},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2791000008583069}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6693000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4702000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.295199990272522},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2777796192","wikidata":"https://www.wikidata.org/wiki/Q5419665","display_name":"Exclosure","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.62","pdf_url":"https://aclanthology.org/2024.findings-eacl.62.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.62","pdf_url":"https://aclanthology.org/2024.findings-eacl.62.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126447459.pdf","grobid_xml":"https://content.openalex.org/works/W7126447459.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"language":[1,52,67,120],"models":[2,20],"(LMs)":[3],"are":[4],"notoriously":[5],"susceptible":[6],"to":[7,57,118,164,180],"generating":[8],"hallucinated":[9,39,101,145,175],"information.Such":[10],"inaccurate":[11],"outputs":[12],"not":[13],"only":[14],"undermine":[15],"the":[16,48,119,123,152,159],"reliability":[17],"of":[18,51,113,154],"these":[19,171],"but":[21],"also":[22,148],"limit":[23],"their":[24,58,184],"use":[25],"and":[26,32,41,44,60,86,187],"raise":[27],"serious":[28],"concerns":[29],"about":[30,83,122],"misinformation":[31],"propaganda.In":[33],"this":[34,92,157],"work,":[35],"we":[36,95],"focus":[37],"on":[38,183],"book":[40],"article":[42],"references":[43,102,176],"present":[45],"them":[46],"as":[47,129],"\"model":[49],"organism\"":[50],"model":[53,68,121],"hallucination":[54],"research,":[55],"due":[56],"frequent":[59],"easy-to-discern":[61],"nature.We":[62],"posit":[63],"that":[64,97,134],"if":[65],"a":[66,70,111],"cites":[69],"particular":[71],"reference":[72],"in":[73],"its":[74,84],"output,":[75],"then":[76],"it":[77,167],"should":[78],"ideally":[79],"possess":[80],"sufficient":[81],"information":[82],"authors":[85,153],"content,":[87],"among":[88],"other":[89],"relevant":[90],"details.Using":[91],"basic":[93],"insight,":[94],"illustrate":[96],"one":[98],"can":[99,126,161,177,189],"identify":[100],"without":[103],"ever":[104],"consulting":[105],"any":[106],"external":[107],"resources,":[108],"by":[109],"asking":[110],"set":[112],"direct":[114],"or":[115],"indirect":[116],"queries":[117,125],"references.These":[124],"be":[127,162,178,190],"considered":[128],"\"consistency":[130],"checks.\"Our":[131],"findings":[132,172],"highlight":[133],"while":[135],"LMs,":[136],"including":[137],"GPT-4,":[138],"often":[139,149],"produce":[140],"inconsistent":[141],"author":[142],"lists":[143],"for":[144],"references,":[146],"they":[147],"accurately":[150],"recall":[151],"real":[155],"references.In":[156],"sense,":[158],"LM":[160],"said":[163],"\"know\"":[165],"when":[166],"is":[168],"hallucinating":[169],"references.Furthermore,":[170],"show":[173],"how":[174],"dissected":[179],"shed":[181],"light":[182],"nature.Replication":[185],"code":[186],"results":[188],"found":[191],"at":[192],"github.com/microsoft/hallucinatedreferences.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}