{"id":"https://openalex.org/W4399365038","doi":"https://doi.org/10.1145/3630106.3658932","title":"Auditing GPT's Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show?","display_name":"Auditing GPT's Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show?","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399365038","doi":"https://doi.org/10.1145/3630106.3658932"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658932","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3630106.3658932","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099025196","display_name":"Yaaseen Mahomed","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaaseen Mahomed","raw_affiliation_strings":["University of Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0009-0005-0295-3803","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, USA","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099025197","display_name":"Charlie M. Crawford","orcid":"https://orcid.org/0009-0007-3955-0316"},"institutions":[{"id":"https://openalex.org/I155707491","display_name":"Haverford College","ror":"https://ror.org/04fnrxr62","country_code":"US","type":"education","lineage":["https://openalex.org/I155707491"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlie M. Crawford","raw_affiliation_strings":["Haverford College, USA"],"raw_orcid":"https://orcid.org/0009-0007-3955-0316","affiliations":[{"raw_affiliation_string":"Haverford College, USA","institution_ids":["https://openalex.org/I155707491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012346367","display_name":"Sanjana Gautam","orcid":"https://orcid.org/0000-0002-2933-304X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjana Gautam","raw_affiliation_strings":["Pennsylvania State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-2933-304X","affiliations":[{"raw_affiliation_string":"Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086384189","display_name":"Sorelle A. Friedler","orcid":"https://orcid.org/0000-0001-6023-1597"},"institutions":[{"id":"https://openalex.org/I155707491","display_name":"Haverford College","ror":"https://ror.org/04fnrxr62","country_code":"US","type":"education","lineage":["https://openalex.org/I155707491"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sorelle A. Friedler","raw_affiliation_strings":["Haverford College, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6023-1597","affiliations":[{"raw_affiliation_string":"Haverford College, United States of America","institution_ids":["https://openalex.org/I155707491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086524212","display_name":"Dana\u00eb Metaxa","orcid":"https://orcid.org/0000-0001-9359-6090"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dana\u00eb Metaxa","raw_affiliation_strings":["University of Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-9359-6090","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, United States of America","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9856,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97245606,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"660","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.8343851566314697},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7883342504501343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648046970367432},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6098105311393738},{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.5918946266174316},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5581823587417603},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5200119018554688},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.44463565945625305},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2581423819065094},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1664852797985077},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.1168251633644104},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.09450069069862366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09023424983024597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08963122963905334}],"concepts":[{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.8343851566314697},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7883342504501343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648046970367432},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6098105311393738},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.5918946266174316},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5581823587417603},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5200119018554688},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.44463565945625305},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2581423819065094},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1664852797985077},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.1168251633644104},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09450069069862366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09023424983024597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08963122963905334},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630106.3658932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658932","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658932","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2149252982","https://openalex.org/W2340954483","https://openalex.org/W2487598231","https://openalex.org/W2550925836","https://openalex.org/W2595653137","https://openalex.org/W2751936342","https://openalex.org/W2766822006","https://openalex.org/W2791170418","https://openalex.org/W2893425640","https://openalex.org/W2920807444","https://openalex.org/W2940406222","https://openalex.org/W2949678053","https://openalex.org/W2956090150","https://openalex.org/W2957654274","https://openalex.org/W2962787423","https://openalex.org/W2965280546","https://openalex.org/W2972668795","https://openalex.org/W2995382404","https://openalex.org/W3003162384","https://openalex.org/W3011762034","https://openalex.org/W3035346764","https://openalex.org/W3047811477","https://openalex.org/W3094002940","https://openalex.org/W3125817989","https://openalex.org/W3133702157","https://openalex.org/W3159059608","https://openalex.org/W3159435787","https://openalex.org/W3165288160","https://openalex.org/W3170344956","https://openalex.org/W3175487198","https://openalex.org/W3215475614","https://openalex.org/W4212771719","https://openalex.org/W4226278401","https://openalex.org/W4287634470","https://openalex.org/W4287674181","https://openalex.org/W4290943938","https://openalex.org/W4293065604","https://openalex.org/W4308391526","https://openalex.org/W4309618884","https://openalex.org/W4323043839","https://openalex.org/W4377157114","https://openalex.org/W4380319657","https://openalex.org/W4382318449","https://openalex.org/W4385985242","https://openalex.org/W4386925532","https://openalex.org/W4388108510","https://openalex.org/W6782465632"],"related_works":["https://openalex.org/W2946613364","https://openalex.org/W2807886874","https://openalex.org/W1697346018","https://openalex.org/W2113326855","https://openalex.org/W4393527151","https://openalex.org/W611259847","https://openalex.org/W2354785495","https://openalex.org/W642986199","https://openalex.org/W2320858910","https://openalex.org/W174528541"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,29],"(LLMs)":[3],"are":[4,44,229],"increasingly":[5],"appearing":[6],"in":[7,24,52,126,148,153],"consumer-facing":[8],"products.":[9],"To":[10,97],"prevent":[11,27],"problematic":[12],"use,":[13],"the":[14,28,53,72,84,127,149,177,243],"organizations":[15],"behind":[16],"these":[17,39,57],"systems":[18],"have":[19,63],"put":[20],"content":[21,32,60,90,139,146,199],"moderation":[22,61,91,140,255],"guardrails":[23,92],"place":[25],"that":[26,188,215],"from":[30,176],"generating":[31],"they":[33,47],"consider":[34],"harmful.":[35],"However,":[36],"most":[37],"of":[38,56,71,80,86,105,111,130,192,203,208,237,245],"enforcement":[40],"standards":[41],"and":[42,93,152,194,206,227,248],"processes":[43],"opaque.":[45],"Although":[46],"play":[48],"a":[49,101,109,161,189,234],"major":[50],"role":[51],"user":[54],"experience":[55],"tools,":[58],"automated":[59],"tools":[62],"received":[64],"relatively":[65],"less":[66],"attention":[67],"than":[68],"other":[69],"aspects":[70],"models.":[73],"This":[74],"study":[75],"undertakes":[76],"an":[77],"algorithm":[78],"audit":[79],"OpenAI\u2019s":[81],"ChatGPT":[82],"with":[83,118,169],"goal":[85],"better":[87],"understanding":[88],"its":[89],"their":[94,254],"potential":[95],"biases.":[96],"evaluate":[98],"performance":[99],"on":[100,164,172,253],"broad":[102],"cultural":[103],"range":[104],"content,":[106],"we":[107,213],"generate":[108,160],"dataset":[110],"100":[112],"popular":[113],"United":[114],"States":[115],"television":[116],"shows":[117,180],"one":[119],"to":[120,143,159,233],"three":[121],"synopses":[122,150],"for":[123,250],"each":[124,131,165],"episode":[125],"first":[128],"season":[129],"show":[132,187],"(3,309":[133],"total":[134,182],"synopses).":[135],"We":[136,239],"probe":[137],"GPT\u2019s":[138,154],"endpoint":[141],"(ME)":[142],"identify":[144],"violating":[145],"both":[147],"themselves,":[151],"own":[155],"outputs":[156,171],"when":[157],"asked":[158],"script":[162],"based":[163],"synopsis,":[166],"also":[167],"comparing":[168],"ME":[170,183],"81":[173],"real":[174,195,209],"scripts":[175,196,205],"same":[178],"TV":[179,216],"(269,578":[181],"outputs).":[184],"Our":[185],"findings":[186],"large":[190],"number":[191],"GPT-generated":[193],"flag":[197],"as":[198,219,221],"violations":[200],"(about":[201],"18%":[202],"GPT":[204],"69%":[207],"ones).":[210],"Using":[211],"metadata,":[212],"find":[214],"maturity":[217],"ratings,":[218],"well":[220],"certain":[222],"genres":[223],"(Animation,":[224],"Crime,":[225],"Fantasy,":[226],"others)":[228],"statistically":[230],"significantly":[231],"related":[232],"script\u2019s":[235],"likelihood":[236],"flagging.":[238],"conclude":[240],"by":[241],"discussing":[242],"implications":[244],"LLM":[246],"self-censorship":[247],"directions":[249],"future":[251],"research":[252],"procedures.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}