{"id":"https://openalex.org/W4417296676","doi":"https://doi.org/10.1016/j.eswa.2026.132995","title":"Textual data bias detection and mitigation - an extensible pipeline with experimental evaluation","display_name":"Textual data bias detection and mitigation - an extensible pipeline with experimental evaluation","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W4417296676","doi":"https://doi.org/10.1016/j.eswa.2026.132995"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132995","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132995","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.eswa.2026.132995","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092838815","display_name":"Rebekka G\u00f6rge","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Rebekka G\u00f6rge","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0008-3793-1374","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020613750","display_name":"Sujan Sai Gannamaneni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sujan Sai Gannamaneni","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0008-0257-4530","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120792367","display_name":"Tabea Naeven","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tabea Naeven","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0001-3471-3389","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071912952","display_name":"Hammam Abdelwahab","orcid":"https://orcid.org/0009-0000-6283-2310"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hammam Abdelwahab","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0000-6283-2310","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043402158","display_name":"H\u00e9ctor Allende\u2010Cid","orcid":"https://orcid.org/0000-0003-3047-8817"},"institutions":[{"id":"https://openalex.org/I4210116133","display_name":"Pontificial Catholic University of Valparaiso","ror":null,"country_code":"CL","type":null,"lineage":["https://openalex.org/I4210116133"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["CL","DE"],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Allende-Cid","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","Pontificia Universidad Cat\u00f3lica de Valpara\u00edso - Av. Brasil 2950, 2340025, Valpara\u00edso, Chile"],"raw_orcid":"https://orcid.org/0000-0003-3047-8817","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Valpara\u00edso - Av. Brasil 2950, 2340025, Valpara\u00edso, Chile","institution_ids":["https://openalex.org/I4210116133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046710","display_name":"Armin B. Cremers","orcid":"https://orcid.org/0000-0002-7693-4649"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Armin B. Cremers","raw_affiliation_strings":["B-IT Emeritus Research Group AI Foundations, University of Bonn, Friedrich-Hirzebruch-Allee 6, 53115, Bonn, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7693-4649","affiliations":[{"raw_affiliation_string":"B-IT Emeritus Research Group AI Foundations, University of Bonn, Friedrich-Hirzebruch-Allee 6, 53115, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114285221","display_name":"Lennard Helmer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lennard Helmer","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0009-2411-4540","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062749833","display_name":"Michael M\u00f6ck","orcid":"https://orcid.org/0009-0009-9864-8924"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Mock","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7352-9165","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025884102","display_name":"Anna Schmitz","orcid":"https://orcid.org/0000-0001-8801-3700"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anna Schmitz","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8801-3700","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001536739","display_name":"Songkai Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songkai Xue","raw_affiliation_strings":["Trustworthiness Theory, Technology & Engineering Lab, Huawei Technologies Co., Ltd, 201718, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-6534-1180","affiliations":[{"raw_affiliation_string":"Trustworthiness Theory, Technology & Engineering Lab, Huawei Technologies Co., Ltd, 201718, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120792366","display_name":"Elif Yildirir","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elif Yildirir","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0004-1201-1484","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035196367","display_name":"Maximilian Poretschkin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Poretschkin","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0009-0004-9038-1835","affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108279292","display_name":"Stefan Wrobel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wrobel","raw_affiliation_strings":["Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Intelligent Analysis and Information Systems - Schloss, Birlinghoven 1, 53757, Sankt, Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]},{"raw_affiliation_string":"Lamarr Institute for Machine Learning and Artificial Intelligence - Schloss Birlinghoven 1, 53757, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092838815"],"corresponding_institution_ids":["https://openalex.org/I4210144576"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02160838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"330","issue":null,"first_page":"132995","last_page":"132995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3400000035762787,"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/T10028","display_name":"Topic Modeling","score":0.3400000035762787,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.1527000069618225,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.08869999647140503,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.9503999948501587},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.555899977684021},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5322999954223633},{"id":"https://openalex.org/keywords/operationalization","display_name":"Operationalization","score":0.5227000117301941},{"id":"https://openalex.org/keywords/non-response-bias","display_name":"Non-response bias","score":0.46399998664855957},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.45210000872612},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.44859999418258667},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.40560001134872437},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9503999948501587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5322999954223633},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C134801348","wikidata":"https://www.wikidata.org/wiki/Q7140425","display_name":"Non-response bias","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C198477413","wikidata":"https://www.wikidata.org/wiki/Q7647069","display_name":"Survey data collection","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C159447121","wikidata":"https://www.wikidata.org/wiki/Q490535","display_name":"Response bias","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.eswa.2026.132995","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132995","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2512.10734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10734","pdf_url":"https://arxiv.org/pdf/2512.10734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2512.10734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10734","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.eswa.2026.132995","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132995","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Textual":[0],"data":[1,57,69,155,185,210,235],"used":[2],"to":[3,91,95,237],"train":[4],"large":[5],"language":[6,15],"models":[7,193],"(LLMs)":[8],"exhibits":[9],"multifaceted":[10],"bias":[11,58,70,74,102,124,171,189,218],"manifestations,":[12],"encompassing":[13],"harmful":[14],"and":[16,29,49,60,75,113,127,141,160,172,229],"skewed":[17],"demographic":[18],"distributions.":[19],"Regulations":[20],"such":[21],"as":[22,143],"the":[23,38,106,148,182,198,231],"EU":[24],"AI":[25],"Act":[26],"require":[27],"identifying":[28],"mitigating":[30],"biases":[31],"against":[32],"protected":[33],"groups":[34],"in":[35,175,225],"data,":[36],"with":[37],"ultimate":[39],"goal":[40],"of":[41,150,184],"preventing":[42],"unfair":[43],"model":[44,188,240],"outputs.":[45],"However,":[46],"practical":[47],"guidance":[48],"operationalization":[50],"are":[51],"lacking.":[52],"We":[53,132],"propose":[54],"a":[55,79,134,176],"comprehensive":[56],"detection":[59],"mitigation":[61],"pipeline":[62],"comprising":[63],"four":[64],"components":[65],"that":[66,166,205],"address":[67,238],"two":[68],"types,":[71],"namely":[72],"representation":[73,101,123,170],"(explicit)":[76,173],"stereotypes":[77,115,174],"for":[78,233],"configurable":[80],"sensitive":[81],"attribute.":[82],"First,":[83,145],"we":[84,111,121,146,167,180],"leverage":[85],"LLM-generated":[86],"word":[87],"lists,":[88],"created":[89],"according":[90],"defined":[92],"quality":[93],"criteria,":[94],"detect":[96,112],"relevant":[97],"group":[98],"labels.":[99],"Second,":[100,179],"is":[103],"quantified":[104],"using":[105,116,137],"Demographic":[107],"Representation":[108],"Score.":[109],"Third,":[110],"mitigate":[114,122],"sociolinguistically":[117],"informed":[118],"filtering.":[119],"Finally,":[120],"through":[125,157],"Grammar-":[126],"Context-Aware":[128],"Counterfactual":[129],"Data":[130],"Augmentation.":[131],"conduct":[133],"twofold":[135],"evaluation":[136,203,227],"gender,":[138],"religion":[139],",":[140],"age":[142],"examples.":[144],"evaluate":[147,181],"effectiveness":[149],"each":[151],"individual":[152],"component":[153],"on":[154,187,197,208,217],"debiasing":[156,186],"human":[158],"validation":[159],"baseline":[161],"comparison.":[162],"The":[163],"findings":[164],"demonstrate":[165],"successfully":[168],"reduce":[169],"text":[177,200],"dataset.":[178,201],"effect":[183],"by":[190],"benchmarking":[191],"several":[192],"(0.6B-8B":[194],"parameters)":[195],"fine-tuned":[196,207],"debiased":[199,209],"This":[202],"reveals":[204],"LLMs":[206],"do":[211],"not":[212],"consistently":[213],"show":[214],"improved":[215],"performance":[216],"benchmarks.":[219],"These":[220],"results":[221],"expose":[222],"critical":[223],"gaps":[224],"current":[226],"methodologies":[228],"highlight":[230],"need":[232],"targeted":[234],"interventions":[236],"manifested":[239],"bias.":[241]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-12-13T00:00:00"}