{"id":"https://openalex.org/W4406459488","doi":"https://doi.org/10.1109/bigdata62323.2024.10825770","title":"JSocialFact: a Misinformation dataset from Social Media for Benchmarking LLM Safety","display_name":"JSocialFact: a Misinformation dataset from Social Media for Benchmarking LLM Safety","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459488","doi":"https://doi.org/10.1109/bigdata62323.2024.10825770"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5113281910","display_name":"Tomoka Nakazato","orcid":"https://orcid.org/0009-0005-3998-6430"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoka Nakazato","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109273211","display_name":"M. Onishi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Onishi","raw_affiliation_strings":["Artificial Intelligence Research Center,AIST,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center,AIST,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100887075","display_name":"Hisami Suzuki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisami Suzuki","raw_affiliation_strings":["NII LLMC,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NII LLMC,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018083511","display_name":"Yuya Shibuya","orcid":"https://orcid.org/0000-0003-4610-2689"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Shibuya","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22144996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3017","last_page":"3025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9980000257492065,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9980000257492065,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9973999857902527,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9887999892234802,"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/misinformation","display_name":"Misinformation","score":0.8710477352142334},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8521865010261536},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.8160360455513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5891523361206055},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35985809564590454},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21219393610954285},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.20600786805152893},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.14134368300437927}],"concepts":[{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.8710477352142334},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8521865010261536},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.8160360455513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891523361206055},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35985809564590454},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21219393610954285},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.20600786805152893},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.14134368300437927},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3087305044","https://openalex.org/W3201174429","https://openalex.org/W4226412112","https://openalex.org/W4281690148","https://openalex.org/W4319983294","https://openalex.org/W4385571050","https://openalex.org/W4386566590","https://openalex.org/W4392353733","https://openalex.org/W4395071714","https://openalex.org/W4399205584","https://openalex.org/W4399414932","https://openalex.org/W4399911158","https://openalex.org/W4400434225","https://openalex.org/W6868537965","https://openalex.org/W6869628718"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W3197131596","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W4390616380"],"abstract_inverted_index":{"The":[0,82],"emergence":[1],"of":[2,19,34,74,102,170],"large":[3],"language":[4],"models":[5,124],"(LLM)":[6],"has":[7],"given":[8],"rise":[9],"to":[10,46,166],"a":[11,29,68,99],"growing":[12],"concern":[13],"regarding":[14],"the":[15,32,49,72,89,153,168],"generation":[16],"and":[17,52,95,115],"dissemination":[18],"inaccurate":[20],"information":[21,54,79,107],"through":[22],"these":[23],"technologies.":[24],"Addressing":[25],"this":[26],"issue":[27],"requires":[28],"benchmark":[30,69,83],"for":[31,36,70],"safety":[33,73,146,169],"LLM":[35,75,171],"Japanese.":[37],"However,":[38],"existing":[39],"benchmarks":[40],"are":[41,56],"limited":[42],"in":[43,62,80,122,162,173],"that":[44,55],"fail":[45],"adequately":[47],"incorporate":[48],"unique":[50],"falsehoods":[51],"erroneous":[53],"actively":[57],"circulating":[58,109],"on":[59,77,110],"social":[60,111,159],"media":[61,160],"Japan.":[63,81],"This":[64],"study":[65],"proposes":[66],"JSocialFact,":[67],"evaluating":[71],"based":[76],"misleading":[78],"is":[84,152],"created":[85],"by":[86],"manually":[87],"annotating":[88],"data":[90],"extracted":[91],"from":[92,157],"X":[93],"posts":[94],"community":[96],"notes":[97],"capturing":[98],"wide":[100],"range":[101],"misleading,":[103],"false,":[104],"or":[105],"malicious":[106],"currently":[108],"media.":[112],"Both":[113],"manual":[114],"automatic":[116],"evaluations":[117],"using":[118],"GPT-4":[119,142],"revealed":[120],"discrepancies":[121,138],"how":[123],"handle":[125],"harmful":[126],"content.":[127],"Although":[128],"GPT-4\u2019s":[129],"evaluation":[130],"showed":[131],"some":[132],"correlation":[133],"with":[134,141],"human":[135,149],"judgment,":[136],"notable":[137],"were":[139],"observed,":[140],"frequently":[143],"assigning":[144],"higher":[145],"scores":[147],"than":[148],"evaluators.":[150],"JSocialFact":[151],"first":[154],"dataset":[155],"constructed":[156],"actual":[158],"logs":[161],"Japanese,":[163],"specifically":[164],"designed":[165],"evaluate":[167],"outputs":[172],"addressing":[174],"misinformation.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}