{"id":"https://openalex.org/W4416035898","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.2","title":"Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification","display_name":"Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035898","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.2"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.2","pdf_url":"https://aclanthology.org/2025.findings-emnlp.2.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.2.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067751383","display_name":"Takuma Udagawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuma Udagawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528325","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-3774-6773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586444","display_name":"Hiroshi Kanayama","orcid":"https://orcid.org/0000-0001-8183-5090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Kanayama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069125151","display_name":"Bishwaranjan Bhattacharjee","orcid":"https://orcid.org/0009-0009-7097-4891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bishwaranjan Bhattacharjee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30403643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.060600001364946365,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.060600001364946365,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.04820000007748604,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.04610000178217888,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/feature","display_name":"Feature (linguistics)","score":0.323199987411499},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.27730000019073486},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27140000462532043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2606000006198883},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.24539999663829803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.489300012588501},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.24539999663829803},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.23970000445842743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23720000684261322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.2","pdf_url":"https://aclanthology.org/2025.findings-emnlp.2.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.2","pdf_url":"https://aclanthology.org/2025.findings-emnlp.2.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035898.pdf","grobid_xml":"https://content.openalex.org/works/W4416035898.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,66],"models":[2],"(LLMs)":[3],"acquire":[4],"general":[5],"linguistic":[6],"knowledge":[7],"from":[8],"massive-scale":[9],"pretraining.However,":[10],"pretraining":[11,47,92],"data":[12],"mainly":[13],"comprised":[14],"of":[15,51,77,98],"web-crawled":[16],"texts":[17],"contain":[18],"undesirable":[19],"social":[20,43,99],"biases":[21,44,100],"which":[22],"can":[23],"be":[24,103],"perpetuated":[25],"or":[26,105],"even":[27],"amplified":[28],"by":[29,60],"LLMs.In":[30],"this":[31],"study,":[32],"we":[33,73],"propose":[34],"an":[35],"efficient":[36],"yet":[37],"effective":[38],"annotation":[39],"pipeline":[40,49],"to":[41,55,63],"investigate":[42],"in":[45],"the":[46,65,75,89],"corpora.Our":[48],"consists":[50],"protected":[52],"attribute":[53],"detection":[54],"identify":[56],"diverse":[57],"demographics,":[58],"followed":[59],"regard":[61],"classification":[62],"analyze":[64],"polarity":[67],"towards":[68],"each":[69],"attribute.Through":[70],"our":[71,78],"experiments,":[72],"demonstrate":[74],"effect":[76],"bias":[79],"analysis":[80],"and":[81],"mitigation":[82],"measures,":[83],"focusing":[84],"on":[85],"Common":[86],"Crawl":[87],"as":[88],"most":[90],"representative":[91],"corpus.Warning:":[93],"This":[94],"paper":[95],"contains":[96],"examples":[97],"that":[101],"may":[102],"harmful":[104],"offensive.":[106]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}