{"id":"https://openalex.org/W4412886686","doi":"https://doi.org/10.18653/v1/2025.acl-long.193","title":"Do Large Language Models have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","display_name":"Do Large Language Models have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886686","doi":"https://doi.org/10.18653/v1/2025.acl-long.193"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.193","pdf_url":"https://aclanthology.org/2025.acl-long.193.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.193.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079620773","display_name":"Yanzhu Guo","orcid":"https://orcid.org/0000-0002-5207-2933"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yanzhu Guo","raw_affiliation_strings":["Inria Paris","\u00c9cole Polytechnique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Paris","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"\u00c9cole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056508457","display_name":"Simone Conia","orcid":"https://orcid.org/0000-0002-6238-7816"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Conia","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089075841","display_name":"Zelin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zelin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400714","display_name":"Min Li","orcid":"https://orcid.org/0000-0001-9406-4707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044514249","display_name":"Saloni Potdar","orcid":"https://orcid.org/0009-0006-0607-6104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saloni Potdar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5116820647","display_name":"Henry Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henry Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.6164,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98691808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3823","last_page":"3838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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/naturalness","display_name":"Naturalness","score":0.94368976354599},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.778529167175293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.659270167350769},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5796297788619995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4641849398612976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41242408752441406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.24077147245407104}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.94368976354599},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.778529167175293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659270167350769},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5796297788619995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4641849398612976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41242408752441406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.24077147245407104},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.193","pdf_url":"https://aclanthology.org/2025.acl-long.193.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.193","pdf_url":"https://aclanthology.org/2025.acl-long.193.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886686.pdf","grobid_xml":"https://content.openalex.org/works/W4412886686.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Current":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"are":[5,19],"predominantly":[6],"designed":[7],"with":[8],"English":[9],"as":[10],"the":[11,16,55,60,84,133,151,158,168],"primary":[12],"language,":[13,38],"and":[14,53,86,109,127,142,165],"even":[15],"few":[17],"that":[18],"multilingual":[20,63,94,162,172],"tend":[21],"to":[22,82,131],"exhibit":[23],"strong":[24],"English-centric":[25,48],"biases.Much":[26],"like":[27],"speakers":[28],"who":[29],"might":[30],"produce":[31],"awkward":[32],"expressions":[33],"when":[34],"learning":[35],"a":[36,93,104,114,125,139],"second":[37],"LLMs":[39,102],"often":[40],"generate":[41],"unnatural":[42],"outputs":[43,65,91],"in":[44,50,92,107,138,147],"non-English":[45],"languages,":[46],"reflecting":[47],"patterns":[49],"both":[51],"vocabulary":[52],"grammar.Despite":[54],"importance":[56,159],"of":[57,62,89,135,160,171],"this":[58,70,74,120],"issue,":[59,121],"naturalness":[61,88,134,148],"LLM":[64,90,137],"has":[66],"received":[67],"limited":[68],"attention.In":[69],"paper,":[71],"we":[72,99,122],"address":[73],"gap":[75],"by":[76],"introducing":[77],"novel":[78],"automatic":[79],"corpus-level":[80],"metrics":[81],"assess":[83],"lexical":[85],"syntactic":[87],"context.Using":[95],"our":[96],"new":[97,169],"metrics,":[98,163],"evaluate":[100],"state-of-the-art":[101],"on":[103,153],"curated":[105],"benchmark":[106],"French":[108],"Chinese":[110],"1":[111],",":[112],"revealing":[113],"tendency":[115],"towards":[116],"English-influenced":[117],"patterns.To":[118],"mitigate":[119],"also":[123],"propose":[124],"simple":[126],"effective":[128],"alignment":[129],"method":[130],"improve":[132],"an":[136],"target":[140],"language":[141],"domain,":[143],"achieving":[144],"consistent":[145],"improvements":[146],"without":[149],"compromising":[150],"performance":[152],"general-purpose":[154],"benchmarks.Our":[155],"work":[156],"highlights":[157],"developing":[161],"resources":[164],"methods":[166],"for":[167],"wave":[170],"LLMs.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}