{"id":"https://openalex.org/W7140107140","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.222","title":"Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches","display_name":"Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140107140","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.222"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.222","pdf_url":"https://aclanthology.org/2026.findings-eacl.222.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: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.222.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107580401","display_name":"Noopur Zambare","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Noopur Zambare","raw_affiliation_strings":["Department of Computing Science , University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science , University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308827","display_name":"Kiana Aghakasiri","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kiana Aghakasiri","raw_affiliation_strings":["Department of Computing Science , University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science , University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112232786","display_name":"Carissa Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carissa Lin","raw_affiliation_strings":["Department of Computing Science , University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science , University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051152466","display_name":"Carrie Ye","orcid":"https://orcid.org/0000-0002-9858-5398"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210099137","display_name":"Research Canada","ror":"https://ror.org/0103eqz62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210099137"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carrie Ye","raw_affiliation_strings":["Arthritis Research Canada","Department of Medicine , University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arthritis Research Canada","institution_ids":["https://openalex.org/I4210099137"]},{"raw_affiliation_string":"Department of Medicine , University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146927598","display_name":"J Ross Mitchell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J Ross Mitchell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135973805","display_name":"Mohamed Abdalla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Abdalla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.23129584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4242","last_page":"4257"},"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":0.05490000173449516,"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":0.05490000173449516,"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/T13546","display_name":"Census and Population Estimation","score":0.0478999987244606,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.03909999877214432,"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/generalizability-theory","display_name":"Generalizability theory","score":0.5424000024795532},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.29809999465942383},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2720000147819519},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25540000200271606}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4146000146865845},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.25940001010894775},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.222","pdf_url":"https://aclanthology.org/2026.findings-eacl.222.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.222","pdf_url":"https://aclanthology.org/2026.findings-eacl.222.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309907","display_name":"Alberta Health Services","ror":"https://ror.org/02nt5es71"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320319925","display_name":"Arthritis Society","ror":"https://ror.org/00bpw5437"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140107140.pdf","grobid_xml":"https://content.openalex.org/works/W7140107140.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,138],"models":[2,39,59,78,88,124],"(LLMs)":[3],"have":[4],"shown":[5],"strong":[6],"performance":[7,62],"on":[8,126,132],"clinical":[9,160],"deidentification,":[10],"the":[11,142,147],"task":[12],"of":[13,102,122,146],"identifying":[14],"sensitive":[15],"identifiers":[16,91,135],"to":[17,85,106],"protect":[18],"privacy.However,":[19],"previous":[20],"work":[21],"has":[22],"not":[23],"examined":[24],"their":[25],"generalizability":[26],"between":[27],"formats,":[28],"cultures,":[29],"and":[30,49,99,116,129,152,158],"genders.In":[31],"this":[32],"work,":[33],"we":[34,74,114],"systematically":[35],"evaluate":[36],"fine-tuned":[37,81,131],"transformer":[38],"(BERT,":[40],"ClinicalBERT,":[41,128],"ModernBERT),":[42],"small":[43],"LLMs":[44,51],"(Llama":[45],"1-8B,":[46],"Qwen":[47],"1.5-7B),":[48],"large":[50],"(Llama-70B,":[52],"Qwen-72B)":[53],"at":[54],"de-identification.We":[55],"show":[56],"that":[57,76],"smaller":[58,77],"achieve":[60],"comparable":[61],"while":[63],"substantially":[64],"reducing":[65],"inference":[66],"cost,":[67],"making":[68],"them":[69],"more":[70],"practical":[71,154],"for":[72,156],"deployment.Moreover,":[73],"demonstrate":[75],"can":[79],"be":[80],"with":[82,134],"limited":[83],"data":[84],"outperform":[86],"larger":[87],"in":[89,104,111,150],"de-identifying":[90],"drawn":[92],"from":[93,136],"Mandarin,":[94],"Hindi,":[95],"Spanish,":[96],"French,":[97],"Bengali,":[98],"regional":[100],"variations":[101],"English,":[103],"addition":[105],"gendered":[107],"names.To":[108],"improve":[109],"robustness":[110],"multi-cultural":[112],"contexts,":[113],"introduce":[115],"publicly":[117],"release":[118],"BERT-MultiCulture-DEID,":[119],"a":[120],"set":[121],"de-identification":[123],"based":[125],"BERT,":[127],"ModernBERT,":[130],"MIMIC":[133],"multiple":[137],"variants.Our":[139],"findings":[140],"provide":[141],"first":[143],"comprehensive":[144],"quantification":[145],"efficiency-generalizability":[148],"trade-off":[149],"deidentification":[151],"establish":[153],"pathways":[155],"fair":[157],"efficient":[159],"de-identification.":[161]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-02-24T00:00:00"}