{"id":"https://openalex.org/W4402670982","doi":"https://doi.org/10.18653/v1/2024.acl-long.760","title":"GPT is Not an Annotator: The Necessity of Human Annotation in Fairness Benchmark Construction","display_name":"GPT is Not an Annotator: The Necessity of Human Annotation in Fairness Benchmark Construction","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402670982","doi":"https://doi.org/10.18653/v1/2024.acl-long.760"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-long.760","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.760","pdf_url":"https://aclanthology.org/2024.acl-long.760.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.acl-long.760.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075490667","display_name":"Virginia K. Felkner","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Virginia Felkner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107270189","display_name":"J. Thompson","orcid":"https://orcid.org/0000-0003-3972-4789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jennifer Thompson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000874697","display_name":"Jonathan May","orcid":"https://orcid.org/0000-0002-5284-477X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan May","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075490667"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.099,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82220414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"14104","last_page":"14115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9433000087738037,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8307960033416748},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6529471278190613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6450589895248413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27930372953414917},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07113999128341675}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8307960033416748},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6529471278190613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450589895248413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27930372953414917},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07113999128341675},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.acl-long.760","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.760","pdf_url":"https://aclanthology.org/2024.acl-long.760.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-long.760","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.760","pdf_url":"https://aclanthology.org/2024.acl-long.760.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402670982.pdf","grobid_xml":"https://content.openalex.org/works/W4402670982.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2378211422","https://openalex.org/W2358755282","https://openalex.org/W2745001401"],"abstract_inverted_index":{"Social":[0],"biases":[1],"in":[2,14,106,121],"LLMs":[3],"are":[4],"usually":[5],"measured":[6],"via":[7],"bias":[8,62,140],"benchmark":[9,34,63],"datasets.Current":[10],"benchmarks":[11],"have":[12],"limitations":[13],"scope,":[15],"grounding,":[16],"quality,":[17],"and":[18,81,88,101,128],"human":[19,119],"effort":[20,41],"required.Previous":[21],"work":[22,37,76],"has":[23,94],"shown":[24],"success":[25],"with":[26,44,56],"a":[27,61,78],"community-sourced,":[28],"rather":[29],"than":[30],"crowd-sourced,":[31],"approach":[32],"to":[33,67,77,125],"development.However,":[35],"this":[36,98],"still":[38],"required":[39],"considerable":[40],"from":[42,65],"annotators":[43],"relevant":[45],"lived":[46],"experience.This":[47],"paper":[48],"explores":[49],"whether":[50],"an":[51,68,115],"LLM":[52],"(specifically,":[53],"GPT-3.5-Turbo)can":[54],"assist":[55],"the":[57,74,85,136],"task":[58,100],"of":[59,83,135,138],"developing":[60],"dataset":[64],"responses":[66],"open-ended":[69],"community":[70,80,87],"survey.We":[71],"also":[72],"extend":[73],"previous":[75],"new":[79],"set":[82],"biases:":[84],"Jewish":[86],"antisemitism.Our":[89],"analysis":[90],"shows":[91],"that":[92,111,129],"GPT-3.5-Turbo":[93,112],"poor":[95],"performance":[96],"on":[97],"annotation":[99,120],"produces":[102],"unacceptable":[103],"quality":[104],"issues":[105],"its":[107,130],"output.Thus,":[108],"we":[109],"conclude":[110],"is":[113],"not":[114],"appropriate":[116],"substitute":[117],"for":[118],"sensitive":[122],"tasks":[123],"related":[124],"social":[126],"biases,":[127],"use":[131],"actually":[132],"negates":[133],"many":[134],"benefits":[137],"community-sourcing":[139],"benchmarks.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}