{"id":"https://openalex.org/W4385570014","doi":"https://doi.org/10.18653/v1/2023.acl-short.118","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","display_name":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570014","doi":"https://doi.org/10.18653/v1/2023.acl-short.118"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-short.118","doi":"https://doi.org/10.18653/v1/2023.acl-short.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.118","pdf_url":"https://aclanthology.org/2023.acl-short.118.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-short.118.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033311842","display_name":"Nikil Roashan Selvam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikil Selvam","raw_affiliation_strings":["University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090145147","display_name":"Sunipa Dev","orcid":"https://orcid.org/0000-0002-6647-9662","observed_orcids":["https://orcid.org/0000-0002-6647-9662"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunipa Dev","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043628255","display_name":"Daniel Khashabi","orcid":"https://orcid.org/0009-0009-7664-2230","observed_orcids":["https://orcid.org/0009-0009-7664-2230"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Khashabi","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033257344","display_name":"Tushar Khot","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Khot","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072","observed_orcids":["https://orcid.org/0000-0001-5365-0072"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3801,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92258775,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1373","last_page":"1386"},"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":0.9560999870300293,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9560999870300293,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.012400000356137753,"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/T10028","display_name":"Topic Modeling","score":0.00559999980032444,"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/social-bias","display_name":"social bias","score":0.6510000228881836},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.5770000219345093},{"id":"https://openalex.org/keywords/paraphrasing","display_name":"paraphrase","score":0.6000000238418579},{"id":"https://openalex.org/keywords/random-sampling","display_name":"random sampling","score":0.8309999704360962},{"id":"https://openalex.org/keywords/bias-measurement","display_name":"bias measurement","score":0.6330000162124634},{"id":"https://openalex.org/keywords/model-ranking","display_name":"model ranking","score":0.5519999861717224}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6347787976264954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5908490419387817},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.5057821273803711},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.4468989670276642},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4155377447605133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320736885070801},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28650718927383423},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22720283269882202},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.22189030051231384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15248659253120422},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.acl-short.118","doi":"https://doi.org/10.18653/v1/2023.acl-short.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.118","pdf_url":"https://aclanthology.org/2023.acl-short.118.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.10040","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.10040","pdf_url":"https://arxiv.org/pdf/2210.10040","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.10040","doi":"https://doi.org/10.48550/arxiv.2210.10040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.10040","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-short.118","doi":"https://doi.org/10.18653/v1/2023.acl-short.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.118","pdf_url":"https://aclanthology.org/2023.acl-short.118.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4074000120162964,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320317052","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570014.pdf","grobid_xml":"https://content.openalex.org/works/W4385570014.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2005814556","https://openalex.org/W2413794162","https://openalex.org/W2798280648","https://openalex.org/W2889317799","https://openalex.org/W2893425640","https://openalex.org/W2909212904","https://openalex.org/W2950018712","https://openalex.org/W2962753370","https://openalex.org/W2963526187","https://openalex.org/W2965373594","https://openalex.org/W2971307358","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W2981852735","https://openalex.org/W2997588435","https://openalex.org/W3019416653","https://openalex.org/W3020908159","https://openalex.org/W3030163527","https://openalex.org/W3032388710","https://openalex.org/W3039559565","https://openalex.org/W3089430725","https://openalex.org/W3103621845","https://openalex.org/W3154222058","https://openalex.org/W3169618399","https://openalex.org/W3172415559","https://openalex.org/W3174090807","https://openalex.org/W3174651299","https://openalex.org/W3174685870","https://openalex.org/W3177141404","https://openalex.org/W3177189402","https://openalex.org/W3178522238","https://openalex.org/W3184144760","https://openalex.org/W3188785232","https://openalex.org/W3197577761","https://openalex.org/W3198409578","https://openalex.org/W3199609108","https://openalex.org/W3207316473","https://openalex.org/W4220993274","https://openalex.org/W4224308101","https://openalex.org/W4224909334","https://openalex.org/W4226399820","https://openalex.org/W4285162225","https://openalex.org/W4285294416","https://openalex.org/W4304730661","https://openalex.org/W4385574293","https://openalex.org/W4404752288","https://openalex.org/W7047404048"],"related_works":["https://openalex.org/W4389523982","https://openalex.org/W4416035917","https://openalex.org/W4393146522","https://openalex.org/W4416035682","https://openalex.org/W4416445891","https://openalex.org/W4386576667","https://openalex.org/W4402670982","https://openalex.org/W3207316473","https://openalex.org/W7169726968","https://openalex.org/W7223187308"],"abstract_inverted_index":{"How":[0],"reliably":[1],"can":[2],"we":[3,25,56,92],"trust":[4],"the":[5,51,78,103,113],"scores":[6],"obtained":[7],"from":[8,38],"social":[9,17,31,82,86,133],"bias":[10,87,107],"benchmarks":[11,88],"as":[12,72],"faithful":[13],"indicators":[14],"of":[15,80,106,116,132],"problematic":[16],"biases":[18,32,35],"in":[19],"a":[20,63,99],"given":[21,64],"model?In":[22],"this":[23,27],"work,":[24],"study":[26],"question":[28],"by":[29,121],"contrasting":[30],"with":[33],"non-social":[34],"that":[36,76,94],"stem":[37],"choices":[39],"made":[40],"during":[41],"dataset":[42],"construction":[43],"(which":[44],"might":[45],"not":[46],"even":[47],"be":[48],"discernible":[49],"to":[50],"human":[52],"eye).To":[53],"do":[54],"so,":[55],"empirically":[57],"simulate":[58],"various":[59,109],"alternative":[60],"constructions":[61],"for":[62],"benchmark":[65],"based":[66],"on":[67,102],"seemingly":[68],"innocuous":[69],"modifications":[70,97],"(such":[71],"paraphrasing":[73],"or":[74],"random-sampling)":[75],"maintain":[77],"essence":[79],"their":[81],"bias.On":[83],"two":[84],"wellknown":[85],"(WINOGENDER":[89],"and":[90,111],"BIASNLI),":[91],"observe":[93],"these":[95,117,125],"shallow":[96],"have":[98],"surprising":[100],"effect":[101],"resulting":[104],"degree":[105],"across":[108],"models":[110,118],"consequently":[112],"relative":[114],"ordering":[115],"when":[119],"ranked":[120],"measured":[122],"bias.We":[123],"hope":[124],"troubling":[126],"observations":[127],"motivate":[128],"more":[129],"robust":[130],"measures":[131],"biases.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-05T00:00:00"}