{"id":"https://openalex.org/W4412376962","doi":"https://doi.org/10.1145/3726302.3730172","title":"Bias in Language Models: Interplay of Architecture and Data?","display_name":"Bias in Language Models: Interplay of Architecture and Data?","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376962","doi":"https://doi.org/10.1145/3726302.3730172"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730172","doi":"https://doi.org/10.1145/3726302.3730172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730172","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730172","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082642748","display_name":"Mozhgan Talebpour","orcid":"https://orcid.org/0009-0005-9771-4142","observed_orcids":["https://orcid.org/0009-0005-9771-4142"]},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mozhgan Talebpour","raw_affiliation_strings":["University of Essex, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-9771-4142","affiliations":[{"raw_affiliation_string":"University of Essex, London, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001981431","display_name":"Yunfei Long","orcid":"https://orcid.org/0000-0002-4407-578X","observed_orcids":["https://orcid.org/0000-0002-4407-578X"]},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yunfei Long","raw_affiliation_strings":["University of Essex, Colchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4407-578X","affiliations":[{"raw_affiliation_string":"University of Essex, Colchester, United Kingdom","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166161","display_name":"Alba Garc\u00eda Seco de Herrera","orcid":"https://orcid.org/0000-0002-6509-5325","observed_orcids":["https://orcid.org/0000-0002-6509-5325"]},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alba G. Seco De Herrera","raw_affiliation_strings":["National University of Distance Education, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-6509-5325","affiliations":[{"raw_affiliation_string":"National University of Distance Education, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082611298","display_name":"Shoaib Jameel","orcid":"https://orcid.org/0000-0001-7534-3313","observed_orcids":["https://orcid.org/0000-0001-7534-3313"]},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shoaib Jameel","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7534-3313","affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0537,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79283282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2637","last_page":"2641"},"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":0.8496000170707703,"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":0.8496000170707703,"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/T10028","display_name":"Topic Modeling","score":0.07609999924898148,"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":0.022600000724196434,"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/self-attention","display_name":"self-attention","score":0.7599999904632568},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.7400000095367432},{"id":"https://openalex.org/keywords/training-data-bias","display_name":"training data bias","score":0.8289999961853027},{"id":"https://openalex.org/keywords/internal-representations","display_name":"internal representations","score":0.6380000114440918},{"id":"https://openalex.org/keywords/fairness-in-nlp","display_name":"fairness in NLP","score":0.7210000157356262},{"id":"https://openalex.org/keywords/bias-propagation","display_name":"bias propagation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587649822235107},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.691923975944519},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44303980469703674},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39358827471733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3530207872390747},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09191751480102539},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730172","doi":"https://doi.org/10.1145/3726302.3730172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730172","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730172","doi":"https://doi.org/10.1145/3726302.3730172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730172","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5676000118255615}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376962.pdf","grobid_xml":"https://content.openalex.org/works/W4412376962.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2077977857","https://openalex.org/W2164498220","https://openalex.org/W2594739882","https://openalex.org/W2990138404","https://openalex.org/W3000231582","https://openalex.org/W3084269450","https://openalex.org/W4299627282","https://openalex.org/W4317536030","https://openalex.org/W4318046968","https://openalex.org/W4376643691","https://openalex.org/W4386065884","https://openalex.org/W4386783354","https://openalex.org/W4386907007","https://openalex.org/W4389518851","https://openalex.org/W4392362609"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Pre-trained":[0],"language":[1],"models":[2],"(PLMs),":[3],"despite":[4],"showing":[5],"strong":[6],"performance,":[7],"can":[8,14],"carry":[9],"and":[10,21,44,83],"increase":[11],"biases,":[12,95],"which":[13],"limit":[15],"the":[16,27,68,89,96,104,110],"development":[17],"of":[18,30,41,107],"fair":[19],"NLP":[20],"IR":[22],"systems.":[23],"This":[24],"research":[25],"investigates":[26],"foundational":[28],"origins":[29],"bias":[31,108],"within":[32,109],"PLMs,":[33],"moving":[34],"beyond":[35],"detection":[36],"to":[37],"a":[38,50,77,100],"detailed":[39],"analysis":[40],"its":[42],"formation":[43],"propagation":[45],"across":[46],"diverse":[47],"architectures.":[48],"Through":[49],"novel":[51],"attention":[52,58],"weight":[53],"analysis,":[54],"we":[55],"reveal":[56],"distinct":[57],"patterns":[59],"for":[60],"biased":[61],"versus":[62],"neutral":[63],"content,":[64],"offering":[65],"insights":[66],"into":[67],"internal":[69],"representations":[70],"learned":[71],"by":[72],"PLMs.":[73],"Our":[74],"findings":[75],"demonstrate":[76],"complex":[78],"interplay":[79],"between":[80],"training":[81,97],"data":[82,98],"model":[84],"architecture,":[85],"revealing":[86],"that":[87],"while":[88],"transformer's":[90],"self-attention":[91],"mechanism":[92],"amplifies":[93],"existing":[94],"plays":[99],"crucial":[101],"role":[102],"in":[103],"initial":[105],"encoding":[106],"model's":[111],"representations.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}