{"id":"https://openalex.org/W4400450964","doi":"https://doi.org/10.1007/s10994-024-06555-6","title":"Regional bias in monolingual English language models","display_name":"Regional bias in monolingual English language models","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4400450964","doi":"https://doi.org/10.1007/s10994-024-06555-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06555-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06555-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06555-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06555-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111117636","display_name":"Jiachen Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Jiachen Lyu","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055291408","display_name":"Katharina Dost","orcid":"https://orcid.org/0000-0002-1514-0685"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Katharina Dost","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017570709","display_name":"Yun Sing Koh","orcid":"https://orcid.org/0000-0001-7256-4049"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yun Sing Koh","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079908211","display_name":"J\u00f6rg Wicker","orcid":"https://orcid.org/0000-0003-0533-3368"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Wicker","raw_affiliation_strings":["School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Auckland, 38 Princes Street, Auckland, 1010, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111117636"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.729,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75368188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"113","issue":"9","first_page":"6663","last_page":"6696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7032572031021118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820792555809021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5715342164039612},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5382089614868164},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.505591869354248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48787498474121094},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48146310448646545},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2261471450328827},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13858908414840698}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7032572031021118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820792555809021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5715342164039612},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5382089614868164},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.505591869354248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48787498474121094},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48146310448646545},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2261471450328827},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13858908414840698},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-024-06555-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06555-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06555-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06555-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06555-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06555-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G7246367168","display_name":null,"funder_award_id":"C10X2201","funder_id":"https://openalex.org/F4320322784","funder_display_name":"Ministry for Business Innovation and Employment"}],"funders":[{"id":"https://openalex.org/F4320320801","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07"},{"id":"https://openalex.org/F4320322784","display_name":"Ministry for Business Innovation and Employment","ror":"https://ror.org/02jtq1b51"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400450964.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1496253462","https://openalex.org/W2060680671","https://openalex.org/W2094934653","https://openalex.org/W2145979309","https://openalex.org/W2482999929","https://openalex.org/W2483215953","https://openalex.org/W2806163043","https://openalex.org/W2896457183","https://openalex.org/W3023553115","https://openalex.org/W3034485607","https://openalex.org/W3083213769","https://openalex.org/W3092478740","https://openalex.org/W3095730670","https://openalex.org/W3098573764","https://openalex.org/W3099126561","https://openalex.org/W3155266314","https://openalex.org/W3175512496","https://openalex.org/W3176477796","https://openalex.org/W3204432444","https://openalex.org/W3204712960","https://openalex.org/W4206292552","https://openalex.org/W4206783764","https://openalex.org/W4221147496","https://openalex.org/W4233762729","https://openalex.org/W4251845444","https://openalex.org/W4255839052","https://openalex.org/W4285155368","https://openalex.org/W4361982879","https://openalex.org/W4385572757","https://openalex.org/W4388704962","https://openalex.org/W6600960895","https://openalex.org/W6778883912","https://openalex.org/W6835584955"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W2296205523","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Abstract":[0],"In":[1,56],"Natural":[2],"Language":[3],"Processing":[4],"(NLP),":[5],"pre-trained":[6,72],"language":[7],"models":[8,19,143],"(LLMs)":[9],"are":[10,80],"widely":[11],"employed":[12],"and":[13,24,152,206],"refined":[14],"for":[15,94,107],"various":[16],"tasks.":[17,141],"These":[18,129],"have":[20,134],"shown":[21],"considerable":[22],"social":[23],"geographic":[25,114],"biases":[26,39,208],"creating":[27],"skewed":[28],"or":[29],"even":[30,122],"unfair":[31],"representations":[32],"of":[33,83,120],"certain":[34],"groups.":[35],"Research":[36],"focuses":[37],"on":[38,147,179],"toward":[40],"L2":[41],"(English":[42],"as":[43,127,219],"a":[44,98,201],"second":[45],"language)":[46,54],"regions":[47,68,217],"but":[48],"neglects":[49],"bias":[50,65,102],"within":[51,66,165],"L1":[52,67],"(first":[53],"regions.":[55],"this":[57],"work,":[58],"we":[59],"ask":[60],"if":[61,75],"there":[62],"is":[63,169],"regional":[64],"already":[69],"inherent":[70],"in":[71,81,116,123,160,204,210,215],"LLMs":[73],"and,":[74],"so,":[76],"what":[77],"the":[78,117,135,166,188,194],"consequences":[79],"terms":[82],"downstream":[84,140],"model":[85,175],"performance.":[86],"We":[87],"contribute":[88],"an":[89],"investigation":[90],"framework":[91,199],"specifically":[92],"tailored":[93],"low-resource":[95,216],"regions,":[96],"offering":[97],"method":[99],"to":[100,137,171,187],"identify":[101],"without":[103],"imposing":[104],"strict":[105],"requirements":[106],"labeled":[108],"datasets.":[109,196],"Our":[110,197],"research":[111],"reveals":[112],"subtle":[113],"variations":[115],"word":[118,211],"embeddings":[119],"BERT,":[121],"cultures":[124],"traditionally":[125],"perceived":[126],"similar.":[128],"nuanced":[130,162],"features,":[131],"once":[132],"captured,":[133],"potential":[136],"significantly":[138],"impact":[139],"Generally,":[142],"exhibit":[144],"comparable":[145],"performance":[146,154,176],"datasets":[148,158,182,189],"that":[149,173],"share":[150],"similarities,":[151],"conversely,":[153],"may":[155,183],"diverge":[156],"when":[157],"differ":[159],"their":[161],"features":[163,192],"embedded":[164],"language.":[167],"It":[168],"crucial":[170],"note":[172],"estimating":[174],"solely":[177],"based":[178],"standard":[180],"benchmark":[181,195],"not":[184],"necessarily":[185],"apply":[186],"with":[190],"distinct":[191],"from":[193],"proposed":[198],"plays":[200],"pivotal":[202],"role":[203],"identifying":[205],"addressing":[207],"detected":[209],"embeddings,":[212],"particularly":[213],"evident":[214],"such":[218],"New":[220],"Zealand.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
