{"id":"https://openalex.org/W4417225236","doi":"https://doi.org/10.1145/3805689.3812333","title":"Do Chinese models speak Chinese languages?","display_name":"Do Chinese models speak Chinese languages?","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W4417225236","doi":"https://doi.org/10.1145/3805689.3812333"},"language":"en","primary_location":{"id":"doi:10.1145/3805689.3812333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812333","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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3812333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093402679","display_name":"Andrea W Wen-Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Wen-Yi Wang","raw_affiliation_strings":["Cornell Univesity, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0001-6592-1132","affiliations":[{"raw_affiliation_string":"Cornell Univesity, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104621276","display_name":"Unso Eun Seo Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Unso Eun Seo Jo","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0003-2358-243X","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086934220","display_name":"David Mimno","orcid":"https://orcid.org/0000-0001-7510-9404"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mimno","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0001-7510-9404","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0349654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3921","last_page":"3941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09560000151395798,"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":0.09560000151395798,"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":0.08449999988079071,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.07559999823570251,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/china","display_name":"China","score":0.5960000157356262},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.49480000138282776},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.40860000252723694},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.40450000762939453},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.35690000653266907},{"id":"https://openalex.org/keywords/written-language","display_name":"Written language","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C191935318","wikidata":"https://www.wikidata.org/wiki/Q148","display_name":"China","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.37130001187324524},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2780790391","wikidata":"https://www.wikidata.org/wiki/Q1149626","display_name":"Written language","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.34599998593330383},{"id":"https://openalex.org/C2776847045","wikidata":"https://www.wikidata.org/wiki/Q61566","display_name":"Minority language","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2962000072002411},{"id":"https://openalex.org/C206440729","wikidata":"https://www.wikidata.org/wiki/Q4806809","display_name":"Asian studies","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C2775984563","wikidata":"https://www.wikidata.org/wiki/Q6501380","display_name":"Chinese people","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C147600691","wikidata":"https://www.wikidata.org/wiki/Q99274778","display_name":"East Asian languages","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2776618157","wikidata":"https://www.wikidata.org/wiki/Q727694","display_name":"Standard Chinese","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2515999972820282}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3805689.3812333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812333","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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.00289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00289","pdf_url":"https://arxiv.org/pdf/2504.00289","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2504.00289","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.00289","pdf_url":"https://arxiv.org/pdf/2504.00289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"doi:10.48550/arxiv.2504.00289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.00289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3805689.3812333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812333","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 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"release":[1],"of":[2,103,205,229],"top-performing":[3],"open-weight":[4,107,174],"LLMs":[5,175],"has":[6],"cemented":[7],"China's":[8],"role":[9],"as":[10,32,168,200,219,226],"a":[11,78,100,179,227],"leading":[12],"force":[13],"in":[14,23,35,40],"AI":[15],"development.":[16],"Do":[17],"these":[18,133],"models":[19,33,150],"support":[20,28,218],"languages":[21,31,134,162],"spoken":[22,163],"China?":[24],"Or":[25],"do":[26],"they":[27,158],"the":[29,36,74,143,185,191,198,203],"same":[30],"developed":[34],"United":[37],"States":[38],"or":[39],"Europe?":[41],"Comparing":[42],"multilingual":[43,181,224],"capabilities":[44],"is":[45],"important":[46],"for":[47,85,235],"two":[48],"reasons.":[49],"First,":[50],"language":[51,111,217],"ability":[52],"provides":[53],"insights":[54],"into":[55,61],"pre-training":[56],"data":[57],"curation,":[58],"and":[59,64,83,105,117,125,155,170,188,209,231,239],"thus":[60],"resource":[62],"allocation":[63],"development":[65,225],"priorities.":[66],"Second,":[67],"Chinese":[68,95,129,165],"model":[69,96,192,236],"developers":[70,193],"need":[71],"to":[72],"navigate":[73],"tension":[75],"between":[76],"serving":[77],"linguistically":[79],"diverse":[80,186],"population":[81],"domestically,":[82],"optimizing":[84],"globally":[86],"visible":[87],"benchmarks":[88],"that":[89],"are":[90,151],"predominantly":[91],"English.":[92],"We":[93,196],"investigate":[94],"developers'":[97],"priorities":[98],"through":[99],"comparative":[101],"study":[102,177],"Chinese-developed":[104,149],"Western-developed":[106],"LLMs,":[108],"on":[109,122],"21":[110],"variants":[112],"including":[113],"Asian":[114],"regional,":[115],"Chinese,":[116],"European":[118],"languages.":[119],"Our":[120],"experiments":[121],"Information":[123],"Parity":[124],"reading":[126],"comprehension":[127],"show":[128],"models'":[130],"performance":[131,182],"across":[132],"correlates":[135],"strongly":[136],"(r=0.93)":[137],"with":[138,142,202,233],"their":[139],"Western":[140],"counterparts,":[141],"sole":[144],"exception":[145],"being":[146],"better":[147],"Mandarin.":[148],"good":[152],"at":[153],"French":[154],"German,":[156],"but":[157],"sometimes":[159],"cannot":[160],"identify":[161],"by":[164],"minorities":[166],"such":[167],"Kazakh":[169],"Uyghur.":[171],"Overall,":[172],"all":[173],"we":[176],"have":[178],"similar":[180],"profile,":[183],"despite":[184],"linguistic":[187],"cultural":[189],"contexts":[190],"operated":[194],"within.":[195],"interpret":[197],"homogenization":[199],"consistent":[201],"influence":[204],"global":[206],"benchmarking":[207],"practices":[208],"shared":[210],"training":[211],"resources.":[212],"Rather":[213],"than":[214],"treating":[215],"current":[216],"inevitable,":[220],"our":[221],"results":[222],"highlight":[223],"space":[228],"prioritization":[230],"trade-offs,":[232],"implications":[234],"developers,":[237],"policymakers,":[238],"users.":[240]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}