{"id":"https://openalex.org/W4385764438","doi":"https://doi.org/10.24963/ijcai.2023/694","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","display_name":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764438","doi":"https://doi.org/10.24963/ijcai.2023/694"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/694","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/694","pdf_url":"https://www.ijcai.org/proceedings/2023/0694.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0694.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100452654","display_name":"Han Wang","orcid":"https://orcid.org/0000-0001-7347-3763"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Han Wang","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045458136","display_name":"Ming Shan Hee","orcid":"https://orcid.org/0000-0002-6328-5889"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ming Shan Hee","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034501750","display_name":"Md Rabiul Awal","orcid":"https://orcid.org/0000-0002-9668-2733"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Md Rabiul Awal","raw_affiliation_strings":["Mila - Quebec AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila - Quebec AI Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084357603","display_name":"Kenny Tsu Wei Choo","orcid":"https://orcid.org/0000-0003-3845-9143"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kenny Tsu Wei Choo","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089793938","display_name":"Roy Ka-Wei Lee","orcid":"https://orcid.org/0000-0002-1986-7750"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roy Ka-Wei Lee","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100452654"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":4.0442,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95045193,"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":"6255","last_page":"6263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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":1.0,"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/moderation","display_name":"Moderation","score":0.8201854228973389},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.7203344106674194},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.699634313583374},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.5581376552581787},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.5527047514915466},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.516899824142456},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4078478217124939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.356096088886261},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.2500501275062561},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.13555282354354858}],"concepts":[{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.8201854228973389},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7203344106674194},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.699634313583374},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.5581376552581787},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5527047514915466},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.516899824142456},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4078478217124939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.356096088886261},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2500501275062561},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.13555282354354858},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/694","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/694","pdf_url":"https://www.ijcai.org/proceedings/2023/0694.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/694","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/694","pdf_url":"https://www.ijcai.org/proceedings/2023/0694.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764438.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1071251684","https://openalex.org/W2595653137","https://openalex.org/W2740168486","https://openalex.org/W2792441346","https://openalex.org/W2887782043","https://openalex.org/W2949678053","https://openalex.org/W2962990575","https://openalex.org/W2970476646","https://openalex.org/W2989795894","https://openalex.org/W2991138171","https://openalex.org/W3034403876","https://openalex.org/W3034937117","https://openalex.org/W3037822982","https://openalex.org/W3103061166","https://openalex.org/W3118142489","https://openalex.org/W3165660069","https://openalex.org/W3172943453","https://openalex.org/W3173380736","https://openalex.org/W3201375796","https://openalex.org/W3201622928","https://openalex.org/W3205068155","https://openalex.org/W4205332997","https://openalex.org/W4221143046","https://openalex.org/W4281557260","https://openalex.org/W4281623759","https://openalex.org/W4282968607","https://openalex.org/W4285251400","https://openalex.org/W4287257982","https://openalex.org/W4287854450","https://openalex.org/W4287889085","https://openalex.org/W4292779060","https://openalex.org/W4295688927","https://openalex.org/W4304194220","https://openalex.org/W4365420418","https://openalex.org/W4379390687","https://openalex.org/W4382318449"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W2740268725","https://openalex.org/W3093710306","https://openalex.org/W750217911","https://openalex.org/W1970538215","https://openalex.org/W3091547931","https://openalex.org/W2356848460","https://openalex.org/W2030617327","https://openalex.org/W2112487509","https://openalex.org/W2049008714"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"focused":[3],"on":[4,102,167],"using":[5],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"to":[10,49,110,128],"generate":[11,111],"explanations":[12,96,112,143,197],"for":[13,92,113,192,198],"hate":[14,94],"speech":[15,95],"through":[16],"fine-tuning":[17],"or":[18],"prompting.":[19],"Despite":[20],"the":[21,53,130,141,158,168,182,185,190],"growing":[22],"interest":[23],"in":[24,147,178,194],"this":[25,174],"area,":[26],"these":[27,42,162],"generated":[28,44,131],"explanations'":[29],"effectiveness":[30],"and":[31,61,97,116,119,154,172,202],"potential":[32],"limitations":[33],"remain":[34],"poorly":[35],"understood.":[36],"A":[37],"key":[38],"concern":[39],"is":[40,81],"that":[41,75,136],"explanations,":[43,163],"by":[45,58],"LLMs,":[46],"may":[47,176],"lead":[48],"erroneous":[50],"judgments":[51,180],"about":[52,181],"nature":[54,160],"of":[55,79,85,149,161,184],"flagged":[56],"content":[57,62,73,80,199],"both":[59,114],"users":[60],"moderators.":[63],"For":[64],"instance,":[65],"an":[66,89,99],"LLM-generated":[67,196],"explanation":[68],"might":[69],"inaccurately":[70],"convince":[71],"a":[72,76,120],"moderator":[74],"benign":[77],"piece":[78],"hateful.":[82],"In":[83],"light":[84],"this,":[86],"we":[87,107],"propose":[88],"analytical":[90],"framework":[91],"examining":[93],"conducted":[98,123],"extensive":[100],"survey":[101,121],"evaluating":[103],"such":[104],"explanations.":[105,132],"Specifically,":[106],"prompted":[108],"GPT-3":[109],"hateful":[115],"non-hateful":[117],"content,":[118],"was":[122],"with":[124],"2,400":[125],"unique":[126],"respondents":[127],"evaluate":[129],"Our":[133,187],"findings":[134],"reveal":[135],"(1)":[137],"human":[138],"evaluators":[139],"rated":[140],"GPT-generated":[142],"as":[144],"high":[145],"quality":[146],"terms":[148],"linguistic":[150],"fluency,":[151],"informativeness,":[152],"persuasiveness,":[153],"logical":[155],"soundness,":[156],"(2)":[157],"persuasive":[159],"however,":[164],"varied":[165],"depending":[166],"prompting":[169],"strategy":[170],"employed,":[171],"(3)":[173],"persuasiveness":[175],"result":[177],"incorrect":[179],"hatefulness":[183],"content.":[186],"study":[188],"underscores":[189],"need":[191],"caution":[193],"applying":[195],"moderation.":[200],"Code":[201],"results":[203],"are":[204],"available":[205],"at":[206],"https://github.com/Social-AI-Studio/GPT3-HateEval.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
