{"id":"https://openalex.org/W4408564861","doi":"https://doi.org/10.1109/access.2025.3552610","title":"IterDBR: Iterative Generative Dataset Bias Reduction Framework for NLU Models","display_name":"IterDBR: Iterative Generative Dataset Bias Reduction Framework for NLU Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408564861","doi":"https://doi.org/10.1109/access.2025.3552610"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3552610","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552610","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3552610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaoyue Wang","orcid":"https://orcid.org/0009-0007-5230-868X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyue Wang","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0007-5230-868X","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103145862","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0001-7808-3318"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-7808-3318","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0776,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87209365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"66228","last_page":"66237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8359000086784363,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8359000086784363,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.828499972820282,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.8217999935150146,"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/computer-science","display_name":"Computer science","score":0.6304956078529358},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5945705771446228},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5444555878639221},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43267685174942017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38533085584640503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11206138134002686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6304956078529358},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5945705771446228},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5444555878639221},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43267685174942017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38533085584640503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11206138134002686},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3552610","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552610","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:559821c364bf414bbdbada8cebf806a7","is_oa":true,"landing_page_url":"https://doaj.org/article/559821c364bf414bbdbada8cebf806a7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 66228-66237 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3552610","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552610","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2951286828","https://openalex.org/W2962736243","https://openalex.org/W2963096121","https://openalex.org/W2963846996","https://openalex.org/W2963961878","https://openalex.org/W2970019270","https://openalex.org/W2970379526","https://openalex.org/W2984256198","https://openalex.org/W3016970897","https://openalex.org/W3034831508","https://openalex.org/W3035139434","https://openalex.org/W3035695271","https://openalex.org/W3100895823","https://openalex.org/W3105302490","https://openalex.org/W3170037207","https://openalex.org/W3179534853","https://openalex.org/W3204601267","https://openalex.org/W4225468040","https://openalex.org/W4286976735","https://openalex.org/W4382202569","https://openalex.org/W4385571347","https://openalex.org/W4389519104","https://openalex.org/W4404919119","https://openalex.org/W6748164123","https://openalex.org/W6765039553","https://openalex.org/W6765114509","https://openalex.org/W6787241537","https://openalex.org/W6858023062"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Bias":[0,43],"in":[1,14,132,142,145],"natural":[2],"language":[3,79],"understanding":[4],"(NLU)":[5],"models":[6,80],"often":[7],"arises":[8],"from":[9],"reliance":[10],"on":[11,22,122],"spurious":[12],"correlations":[13],"datasets.":[15,147],"Existing":[16],"dataset":[17,51],"refinement":[18],"methods":[19,131],"frequently":[20],"depend":[21],"predefined":[23,57],"biased":[24],"features,":[25],"limiting":[26],"their":[27],"ability":[28,113],"to":[29,82,114],"address":[30,34],"hidden":[31],"biases.":[32],"To":[33],"this,":[35],"we":[36],"introduce":[37],"IterDBR,":[38],"an":[39,62],"Iterative":[40],"Generative":[41],"Dataset":[42],"Reduction":[44],"Framework":[45],"for":[46,56,101],"NLU":[47,124],"Models,":[48],"which":[49],"reduces":[50],"bias":[52,73],"without":[53],"the":[54,72,103,111],"need":[55],"features.":[58],"Our":[59],"approach":[60],"utilizes":[61],"iteratively":[63],"expanded":[64],"sample":[65],"pool":[66],"where":[67],"a":[68],"shallow":[69],"model":[70],"assesses":[71],"levels":[74],"of":[75],"samples,":[76],"leveraging":[77],"large":[78],"(LLMs)":[81],"generate":[83],"pseudo":[84],"samples":[85],"with":[86,136],"fewer":[87],"bias.":[88],"Various":[89],"strategies,":[90],"such":[91],"as":[92],"zero-shot":[93],"prompting,":[94,96],"few-shot":[95],"and":[97,117,134],"fine-tuning,":[98],"were":[99],"explored":[100],"optimizing":[102],"generator\u2019s":[104,112],"performance.":[105],"Notably,":[106],"combining":[107],"these":[108],"strategies":[109],"improved":[110],"create":[115],"diverse":[116,146],"low-bias":[118],"samples.":[119],"Experimental":[120],"results":[121],"three":[123],"tasks":[125],"demonstrate":[126],"that":[127],"IterDBR":[128],"surpasses":[129],"state-of-the-art":[130],"performance":[133],"compatibility":[135],"model-centric":[137],"techniques,":[138],"showcasing":[139],"its":[140],"effectiveness":[141],"mitigating":[143],"biases":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}