{"id":"https://openalex.org/W4412944334","doi":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","title":"Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora","display_name":"Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944334","doi":"https://doi.org/10.18653/v1/2025.gebnlp-1.39"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.gebnlp-1.39","doi":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","pdf_url":"https://aclanthology.org/2025.gebnlp-1.39.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","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/2025.gebnlp-1.39.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033348430","display_name":"Erik Derner","orcid":"https://orcid.org/0000-0002-7588-7668","observed_orcids":["https://orcid.org/0000-0002-7588-7668"]},"institutions":[{"id":"https://openalex.org/I4387155719","display_name":"ELLIS Alicante","ror":"https://ror.org/002ye0093","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4387155719"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Erik Derner","raw_affiliation_strings":["ELLIS Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Alicante , Spain","institution_ids":["https://openalex.org/I4387155719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099362898","display_name":"Sara Sansalvador de la Fuente","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155719","display_name":"ELLIS Alicante","ror":"https://ror.org/002ye0093","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4387155719"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sara Sansalvador De La Fuente","raw_affiliation_strings":["ELLIS Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Alicante , Spain","institution_ids":["https://openalex.org/I4387155719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089001187","display_name":"Yoan Guti\u00e9rrez","orcid":"https://orcid.org/0000-0002-4052-7427","observed_orcids":["https://orcid.org/0000-0002-4052-7427"]},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Yoan Gutierrez","raw_affiliation_strings":["University of Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alicante , Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paloma Moreda Pozo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paloma Moreda Pozo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013727792","display_name":"Nuria Oliver","orcid":"https://orcid.org/0000-0001-5985-691X","observed_orcids":["https://orcid.org/0000-0001-5985-691X"]},"institutions":[{"id":"https://openalex.org/I4387155719","display_name":"ELLIS Alicante","ror":"https://ror.org/002ye0093","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4387155719"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nuria M Oliver","raw_affiliation_strings":["ELLIS Alicante , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELLIS Alicante , Spain","institution_ids":["https://openalex.org/I4387155719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3501,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96383696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"483"},"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":0.7875999808311462,"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":0.7875999808311462,"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/T13173","display_name":"Gender Studies in Language","score":0.07930000126361847,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.033399999141693115,"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/large-language-models","display_name":"large language models","score":0.8550000190734863},{"id":"https://openalex.org/keywords/grammatical-gender","display_name":"grammatical gender","score":0.8769999742507935},{"id":"https://openalex.org/keywords/gendered-language","display_name":"gendered language","score":0.8259999752044678},{"id":"https://openalex.org/keywords/gender-imbalance","display_name":"gender imbalance","score":0.5529999732971191},{"id":"https://openalex.org/keywords/valencian","display_name":"Valencian language","score":0.8970000147819519},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.46000000834465027},{"id":"https://openalex.org/keywords/multilingual-nlp","display_name":"multilingual NLP","score":0.8320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638360857963562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6639519929885864},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6490305066108704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6244735717773438},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5846632719039917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306994318962097},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.504670262336731},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45568063855171204},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17822477221488953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.06700664758682251},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06190001964569092},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.gebnlp-1.39","doi":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","pdf_url":"https://aclanthology.org/2025.gebnlp-1.39.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.13677","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.13677","pdf_url":"https://arxiv.org/pdf/2406.13677","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.13677","doi":"https://doi.org/10.48550/arxiv.2406.13677","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.13677","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.gebnlp-1.39","doi":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.gebnlp-1.39","pdf_url":"https://aclanthology.org/2025.gebnlp-1.39.pdf","source":{"id":"https://openalex.org/S7407087812","display_name":"Workshop on Gender Bias in Natural Language Processing (GeBNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.7307999730110168,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G121809054","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G1915074621","display_name":null,"funder_award_id":"PID2021-122263OB-C22","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2150499748","display_name":null,"funder_award_id":"PID2021-122263OB-C22","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2660406951","display_name":null,"funder_award_id":"/ AEI/10","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G3163637687","display_name":null,"funder_award_id":"PID2021-122263OB-C22","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8272244909","display_name":null,"funder_award_id":"PID2021-123956OB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G8320307401","display_name":null,"funder_award_id":"CIPROM/2021/021","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320311011","display_name":"Universidad de Alicante","ror":"https://ror.org/05t8bcz72"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":null},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":"https://ror.org/003x0zc53"},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944334.pdf","grobid_xml":"https://content.openalex.org/works/W4412944334.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4226462293","https://openalex.org/W4407683970"],"related_works":["https://openalex.org/W4411450382","https://openalex.org/W7152554470","https://openalex.org/W4412889046","https://openalex.org/W7010591754","https://openalex.org/W7223519190","https://openalex.org/W4412944339","https://openalex.org/W4402683156","https://openalex.org/W4402372001","https://openalex.org/W4392426204","https://openalex.org/W4416035294"],"abstract_inverted_index":{"Large":[0],"language":[1,149],"models":[2],"(LLMs)":[3],"often":[4],"inherit":[5],"and":[6,45,93,111,143,155,207],"amplify":[7],"social":[8,16],"biases":[9,168],"embedded":[10],"in":[11,50,80,116,120,147,169,201],"their":[12],"training":[13,72,82,118,170,182],"data.A":[14],"prominent":[15],"bias":[17,31,49,59,89,115,199],"is":[18],"gender":[19,29,42,48,57,113,125,198],"bias.In":[20],"this":[21,101],"regard,":[22],"prior":[23],"work":[24],"has":[25,74],"mainly":[26],"focused":[27],"on":[28,46,183],"stereotyping":[30],"-the":[32,60],"association":[33],"of":[34,63,67,88,129],"specific":[35],"roles":[36],"or":[37,53],"traits":[38],"with":[39],"a":[40,105],"particular":[41],"-in":[43,70],"English":[44],"evaluating":[47],"model":[51,98,173],"embeddings":[52],"generated":[54],"outputs.In":[55],"contrast,":[56],"representation":[58,114],"unequal":[61],"frequency":[62],"references":[64],"to":[65,109,151],"individuals":[66],"different":[68],"genders":[69],"the":[71,81,96,127,135,189,194],"corpora":[73],"received":[75],"less":[76],"attention.Yet":[77],"such":[78,167],"imbalances":[79],"data":[83,119,171,208],"constitute":[84],"an":[85],"upstream":[86],"source":[87],"that":[90,166,185],"can":[91,176],"propagate":[92],"intensify":[94],"throughout":[95],"entire":[97],"lifecycle.To":[99],"fill":[100],"gap,":[102],"we":[103],"propose":[104],"novel":[106],"LLM-based":[107],"method":[108,160],"detect":[110],"quantify":[112],"LLM":[117],"gendered":[121,148],"languages,":[122],"where":[123],"grammatical":[124],"challenges":[126],"applicability":[128],"methods":[130],"developed":[131],"for":[132,196],"English.By":[133],"leveraging":[134,180],"LLMs'":[136],"contextual":[137],"understanding,":[138],"our":[139,159,205],"approach":[140],"automatically":[141],"identifies":[142],"classifies":[144],"person-referencing":[145],"words":[146],"corpora.Applied":[150],"four":[152],"Spanish-English":[153],"benchmarks":[154],"five":[156],"Valencian":[157],"corpora,":[158],"reveals":[161],"substantial":[162],"male-dominant":[163],"imbalances.We":[164],"show":[165],"affect":[172],"outputs,":[174],"but":[175],"surprisingly":[177],"be":[178],"mitigated":[179],"small-scale":[181],"datasets":[184],"are":[186],"biased":[187],"towards":[188],"opposite":[190],"gender.Our":[191],"findings":[192],"highlight":[193],"need":[195],"corpus-level":[197],"analysis":[200],"multilingual":[202],"NLP.We":[203],"make":[204],"code":[206],"publicly":[209],"available":[210],"1":[211],".":[212]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}