{"id":"https://openalex.org/W4415540850","doi":"https://doi.org/10.1145/3746027.3758307","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","display_name":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540850","doi":"https://doi.org/10.1145/3746027.3758307"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758307","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101549512","display_name":"Shuo Yang","orcid":"https://orcid.org/0000-0003-1638-9623"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China and Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1638-9623","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China and Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuqin Dai","orcid":"https://orcid.org/0009-0003-3460-6844"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqin Dai","raw_affiliation_strings":["Tsinghua University, Beijing, China and Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-3460-6844","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guoqing Wang","orcid":"https://orcid.org/0009-0003-8371-0285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-8371-0285","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046631995","display_name":"Xinran Zheng","orcid":"https://orcid.org/0000-0003-1130-7916"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinran Zheng","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1130-7916","affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009892151","display_name":"Jinfeng Xu","orcid":"https://orcid.org/0009-0001-7876-3740"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinfeng Xu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0001-7876-3740","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053796862","display_name":"Jinze Li","orcid":"https://orcid.org/0009-0002-6749-5442"},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinze Li","raw_affiliation_strings":["The University of HongKong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0002-6749-5442","affiliations":[{"raw_affiliation_string":"The University of HongKong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I4210086892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071130920","display_name":"Zhenzhe Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenzhe Ying","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-9624-3776","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080477405","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-6159-619X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqiang Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6159-619X","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077317339","display_name":"Edith C.\u2010H. Ngai","orcid":"https://orcid.org/0000-0002-3454-8731"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Edith C. H. Ngai","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3454-8731","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101549512"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":3.4077,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93580379,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"13435","last_page":"13441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9876000285148621,"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":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7177000045776367},{"id":"https://openalex.org/keywords/misinformation","display_name":"Misinformation","score":0.5583999752998352},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40860000252723694},{"id":"https://openalex.org/keywords/rumor","display_name":"Rumor","score":0.3831000030040741},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7177000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694100022315979},{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C2780469804","wikidata":"https://www.wikidata.org/wiki/Q878352","display_name":"Rumor","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758307","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2977886427","https://openalex.org/W3099977667","https://openalex.org/W3196268181","https://openalex.org/W4382318497","https://openalex.org/W4391047735","https://openalex.org/W4401815218"],"related_works":[],"abstract_inverted_index":{"Large":[0,31],"Language":[1,32],"Models":[2,33],"(LLMs)":[3],"hold":[4],"significant":[5],"potential":[6],"for":[7,133],"advancing":[8],"fact-checking":[9,53,128],"by":[10],"leveraging":[11],"their":[12,124],"capabilities":[13,54],"in":[14,35,126],"reasoning,":[15],"evidence":[16],"retrieval,":[17],"and":[18,29,57,68,84,108,112,120,129],"explanation":[19],"generation.":[20],"However,":[21],"existing":[22],"benchmarks":[23],"fail":[24],"to":[25,50,105],"comprehensively":[26],"evaluate":[27],"LLMs":[28,56,119],"Multimodal":[30],"(MLLMs)":[34],"realistic":[36],"misinformation":[37],"scenarios.":[38],"To":[39],"bridge":[40],"this":[41],"gap,":[42],"we":[43],"introduce":[44],"RealFactBench,":[45],"a":[46,98],"comprehensive":[47],"benchmark":[48],"designed":[49],"assess":[51],"the":[52,92],"of":[55,73,102],"MLLMs":[58,122],"across":[59],"diverse":[60,85],"real-world":[61,127],"tasks,":[62],"including":[63],"Knowledge":[64],"Validation,":[65],"Rumor":[66],"Detection,":[67],"Event":[69],"Verification.":[70],"RealFactBench":[71,136],"consists":[72],"6K":[74],"high-quality":[75],"claims":[76],"drawn":[77],"from":[78],"authoritative":[79],"sources,":[80],"encompassing":[81],"multimodal":[82],"content":[83],"domains.":[86],"Our":[87],"evaluation":[88],"framework":[89],"further":[90,134],"introduces":[91],"Unknown":[93],"Rate":[94],"(UnR)":[95],"metric,":[96],"enabling":[97],"more":[99],"nuanced":[100],"assessment":[101],"models'":[103],"ability":[104],"handle":[106],"uncertainty":[107],"balance":[109],"between":[110],"over-conservatism":[111],"over-confidence.":[113],"Extensive":[114],"experiments":[115],"on":[116],"7":[117],"representative":[118],"4":[121],"reveal":[123],"limitations":[125],"offer":[130],"valuable":[131],"insights":[132],"research.":[135],"is":[137],"publicly":[138],"available":[139],"at":[140],"https://github.com/kalendsyang/RealFactBench.git.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-18T08:16:58.900851","created_date":"2025-10-25T00:00:00"}