{"id":"https://openalex.org/W4396822170","doi":"https://doi.org/10.48550/arxiv.2405.05583","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","display_name":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","publication_year":2024,"publication_date":"2024-05-09","ids":{"openalex":"https://openalex.org/W4396822170","doi":"https://doi.org/10.48550/arxiv.2405.05583"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05583","pdf_url":"http://arxiv.org/pdf/2405.05583","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2405.05583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100631225","display_name":"Yuxia Wang","orcid":"https://orcid.org/0000-0002-6095-1030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033151808","display_name":"Minghan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Minghan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097424556","display_name":"Hasan Iqbal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iqbal, Hasan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406581","display_name":"Georgi Georgiev","orcid":"https://orcid.org/0000-0001-5221-7306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgiev, Georgi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073054282","display_name":"Jiahui Geng","orcid":"https://orcid.org/0000-0002-4205-8230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Jiahui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nakov, Preslav","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9207,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9207,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3973146}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05583","pdf_url":"http://arxiv.org/pdf/2405.05583","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05583","pdf_url":"http://arxiv.org/pdf/2405.05583","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4396696052","https://openalex.org/W4395014643","https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"abstract_inverted_index":{"The":[0],"increased":[1],"use":[2,40],"of":[3,11,22,31,72,90,119],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"across":[8],"a":[9,63,96],"variety":[10],"real-world":[12],"applications":[13],"calls":[14],"for":[15,68,115],"mechanisms":[16],"to":[17,50,79],"verify":[18,86],"the":[19,29,87,117],"factual":[20,88],"accuracy":[21],"their":[23],"outputs.":[24],"Difficulties":[25],"lie":[26],"in":[27,34],"assessing":[28],"factuality":[30,65,102],"free-form":[32],"responses":[33],"open":[35],"domains.":[36],"Also,":[37],"different":[38],"papers":[39],"disparate":[41],"evaluation":[42,66,98],"benchmarks":[43],"and":[44,52,85,92,108],"measurements,":[45],"which":[46],"renders":[47],"them":[48],"hard":[49],"compare":[51],"hampers":[53],"future":[54],"progress.":[55],"To":[56],"mitigate":[57],"these":[58],"issues,":[59],"we":[60],"propose":[61],"OpenFactCheck,":[62],"unified":[64,97],"framework":[67,99],"LLMs.":[69],"OpenFactCheck":[70,127],"consists":[71],"three":[73],"modules:":[74],"(i)":[75],"CUSTCHECKER":[76],"allows":[77],"users":[78],"easily":[80],"customize":[81],"an":[82,112],"automatic":[83,120],"fact-checker":[84],"correctness":[89],"documents":[91],"claims,":[93],"(ii)":[94],"LLMEVAL,":[95],"assesses":[100],"LLM's":[101],"ability":[103],"from":[104],"various":[105],"perspectives":[106],"fairly,":[107],"(iii)":[109],"CHECKEREVAL":[110],"is":[111,128],"extensible":[113],"solution":[114],"gauging":[116],"reliability":[118],"fact-checkers'":[121],"verification":[122],"results":[123],"using":[124],"human-annotated":[125],"datasets.":[126],"publicly":[129],"released":[130],"at":[131],"https://github.com/yuxiaw/OpenFactCheck.":[132]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4396822170","counts_by_year":[],"updated_date":"2025-04-03T02:40:26.522472","created_date":"2024-05-11"}