{"id":"https://openalex.org/W4412945513","doi":"https://doi.org/10.18653/v1/2025.acl-long.458","title":"Instance-Selection-Inspired Undersampling Strategies for Bias Reduction in Small and Large Language Models for Binary Text Classification","display_name":"Instance-Selection-Inspired Undersampling Strategies for Bias Reduction in Small and Large Language Models for Binary Text Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945513","doi":"https://doi.org/10.18653/v1/2025.acl-long.458"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.458","pdf_url":"https://aclanthology.org/2025.acl-long.458.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.458.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070081136","display_name":"Guilherme Fonseca","orcid":"https://orcid.org/0009-0000-7862-8701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guilherme Fonseca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018690278","display_name":"Washington Cunha","orcid":"https://orcid.org/0000-0002-1988-8412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Washington Cunha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114262858","display_name":"Gabriel Prenassi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Prenassi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087565388","display_name":"Leonardo Rocha","orcid":"https://orcid.org/0000-0002-4913-4902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo Chaves Dutra Da Rocha","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":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9323","last_page":"9340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.968999981880188,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.968999981880188,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9222999811172485,"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/undersampling","display_name":"Undersampling","score":0.9316184520721436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7067909836769104},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6663100123405457},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6388444900512695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490765571594238},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5460742115974426},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5281902551651001},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.4390830099582672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38124364614486694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38041746616363525},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21773701906204224},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.18927878141403198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15195327997207642},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08646297454833984}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.9316184520721436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067909836769104},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6663100123405457},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6388444900512695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490765571594238},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5460742115974426},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5281902551651001},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.4390830099582672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38124364614486694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38041746616363525},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21773701906204224},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.18927878141403198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15195327997207642},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08646297454833984},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.458","pdf_url":"https://aclanthology.org/2025.acl-long.458.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.458","pdf_url":"https://aclanthology.org/2025.acl-long.458.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945513.pdf","grobid_xml":"https://content.openalex.org/works/W4412945513.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2109073422","https://openalex.org/W2887783772","https://openalex.org/W2101754595","https://openalex.org/W4249381695","https://openalex.org/W2534887053","https://openalex.org/W2026172757","https://openalex.org/W2080076470","https://openalex.org/W4389292014","https://openalex.org/W2394059563","https://openalex.org/W4297857039"],"abstract_inverted_index":{"Guilherme":[0],"Fonseca,":[1],"Washington":[2],"Cunha,":[3],"Gabriel":[4],"Prenassi,":[5],"Marcos":[6],"Andr\u00e9":[7],"Gon\u00e7alves,":[8],"Leonardo":[9],"Chaves":[10],"Dutra":[11],"Da":[12],"Rocha.":[13],"Proceedings":[14],"of":[15,20],"the":[16,21],"63rd":[17],"Annual":[18],"Meeting":[19],"Association":[22],"for":[23],"Computational":[24],"Linguistics":[25],"(Volume":[26],"1:":[27],"Long":[28],"Papers).":[29],"2025.":[30]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
