{"id":"https://openalex.org/W7131637096","doi":"https://doi.org/10.1145/3772363.3799085","title":"When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models","display_name":"When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7131637096","doi":"https://doi.org/10.1145/3772363.3799085"},"language":null,"primary_location":{"id":"doi:10.1145/3772363.3799085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3799085","pdf_url":null,"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 Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772363.3799085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119688676","display_name":"Satyam Kumar Navneet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164339","display_name":"Oldham Council","ror":"https://ror.org/05cxzzq07","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210164339"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Satyam Kumar Navneet","raw_affiliation_strings":["Independent Researcher, Bihar, India"],"raw_orcid":"https://orcid.org/0009-0000-9852-7174","affiliations":[{"raw_affiliation_string":"Independent Researcher, Bihar, India","institution_ids":["https://openalex.org/I4210164339"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joydeep Chandra","orcid":"https://orcid.org/0009-0009-1909-3263"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joydeep Chandra","raw_affiliation_strings":["BNRIST, Dept. of CST, Tsinghua University, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1909-3263","affiliations":[{"raw_affiliation_string":"BNRIST, Dept. of CST, Tsinghua University, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126856056","display_name":"Yong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["BNRIST, Dept. of CST, Tsinghua University, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8803-2055","affiliations":[{"raw_affiliation_string":"BNRIST, Dept. of CST, Tsinghua University, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.21327801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21559999883174896,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21559999883174896,"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/T12090","display_name":"Language and cultural evolution","score":0.19910000264644623,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/T10028","display_name":"Topic Modeling","score":0.06530000269412994,"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/erasure","display_name":"Erasure","score":0.7265999913215637},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.49230000376701355},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4643999934196472},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45820000767707825},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44920000433921814},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4291999936103821}],"concepts":[{"id":"https://openalex.org/C2778790127","wikidata":"https://www.wikidata.org/wiki/Q484885","display_name":"Erasure","level":2,"score":0.7265999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383000016212463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6072999835014343},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5735999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5156000256538391},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45820000767707825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2777939226","wikidata":"https://www.wikidata.org/wiki/Q7976","display_name":"American English","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3772363.3799085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3799085","pdf_url":null,"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 Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.22145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.22145","pdf_url":"https://arxiv.org/pdf/2602.22145","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2602.22145","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3772363.3799085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772363.3799085","pdf_url":null,"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 Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,122],"increasingly":[5],"used":[6],"to":[7,29,92],"\u201cprofessionalize\u201d":[8],"workplace":[9],"communication,":[10],"often":[11],"at":[12],"the":[13,22],"cost":[14],"of":[15,25,38,85],"linguistic":[16,26],"identity.":[17],"We":[18],"introduce":[19],"\"Cultural":[20],"Ghosting\",":[21],"systematic":[23],"erasure":[24,142],"markers":[27,119,129],"unique":[28],"non-native":[30],"English":[31],"varieties":[32],"during":[33],"text":[34],"processing.":[35],"Through":[36],"analysis":[37],"22,350":[39],"LLM":[40],"outputs":[41],"generated":[42],"from":[43,90],"1,490":[44],"culturally":[45],"marked":[46],"texts":[47],"(Indian,":[48],"Singaporean,&":[49],"Nigerian":[50],"English)":[51],"processed":[52],"by":[53,143],"five":[54],"models":[55,104],"under":[56],"three":[57],"prompt":[58],"conditions,":[59],"we":[60,80,98],"quantify":[61],"this":[62],"phenomenon":[63],"using":[64],"two":[65],"novel":[66],"metrics:":[67],"Identity":[68],"Erasure":[69],"Rate":[70],"(IER)":[71],"&":[72],"Semantic":[73,101],"Preservation":[74,102],"Score":[75],"(SPS).":[76],"Across":[77],"all":[78],"prompts,":[79],"find":[81],"an":[82],"overall":[83],"IER":[84],"10.26%,":[86],"with":[87],"model-level":[88],"variation":[89],"3.5%":[91],"20.5%":[93],"(5.9":[94],"\u00d7":[95,124],"range).":[96],"Crucially,":[97],"identify":[99],"a":[100],"Paradox:":[103],"maintain":[105],"high":[106],"semantic":[107,147],"similarity":[108],"(mean":[109],"SPS":[110],"=":[111],"0.748)":[112],"while":[113],"systematically":[114],"erasing":[115],"cultural":[116],"markers.":[117],"Pragmatic":[118],"(politeness":[120],"conventions)":[121],"1.9":[123],"more":[125],"vulnerable":[126],"than":[127],"lexical":[128],"(71.5%":[130],"vs.":[131],"37.1%":[132],"erasure).":[133],"Our":[134],"experiments":[135],"demonstrate":[136],"that":[137],"explicit":[138],"cultural-preservation":[139],"prompts":[140],"reduce":[141],"29%":[144],"without":[145],"sacrificing":[146],"quality.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-27T00:00:00"}