{"id":"https://openalex.org/W7224401489","doi":"https://doi.org/10.18653/2026.findings-emnlp.793","title":"RegioZH: Unveiling Comprehension Disparities across Regional Chinese Varieties in LLMs","display_name":"RegioZH: Unveiling Comprehension Disparities across Regional Chinese Varieties in LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224401489","doi":"https://doi.org/10.18653/2026.findings-emnlp.793"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.793","doi":"https://doi.org/10.18653/2026.findings-emnlp.793","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.793","pdf_url":"https://aclanthology.org/2026.findings-emnlp.793.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.793.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113059708","display_name":"Weihua Zheng","orcid":"https://orcid.org/0009-0008-5251-5467","observed_orcids":["https://orcid.org/0009-0008-5251-5467"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weihua Zheng","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]},{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160096753","display_name":"Wu Kui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wu Kui","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148811526","display_name":"Thong T. Doan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thong T. Doan","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062452667","display_name":"Lin Jingxia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lin Jingxia","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":"https://orcid.org/0000-0002-2347-0879","observed_orcids":["https://orcid.org/0000-0002-2347-0879"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"AiTi Aw","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877","observed_orcids":["https://orcid.org/0000-0003-0872-5877"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160072555","display_name":"Roy Ka-Wei Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy Ka-Wei Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.88917473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16774","last_page":"16811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4162999987602234,"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":0.4162999987602234,"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":0.3176000118255615,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06700000166893005,"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/large-language-models","display_name":"large language models","score":0.7419999837875366},{"id":"https://openalex.org/keywords/language-comprehension","display_name":"language comprehension","score":0.5360000133514404},{"id":"https://openalex.org/keywords/regional-dialects","display_name":"regional dialects","score":0.6510000228881836},{"id":"https://openalex.org/keywords/language-model-bias","display_name":"bias in language models","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3767000138759613},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3382999897003174},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C191935318","wikidata":"https://www.wikidata.org/wiki/Q148","display_name":"China","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C47768531","wikidata":"https://www.wikidata.org/wiki/Q1127188","display_name":"Development economics","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.26170000433921814},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.26030001044273376},{"id":"https://openalex.org/C45355965","wikidata":"https://www.wikidata.org/wiki/Q1643441","display_name":"Socioeconomics","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.793","doi":"https://doi.org/10.18653/2026.findings-emnlp.793","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.793","pdf_url":"https://aclanthology.org/2026.findings-emnlp.793.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.793","doi":"https://doi.org/10.18653/2026.findings-emnlp.793","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.793","pdf_url":"https://aclanthology.org/2026.findings-emnlp.793.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5983670494","display_name":null,"funder_award_id":"AISG-NMLP-2024-004","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320310946","display_name":"Alberta Agricultural Research Institute","ror":"https://ror.org/01k7fxd28"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224401489.pdf","grobid_xml":"https://content.openalex.org/works/W7224401489.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411541939","https://openalex.org/W4402521700","https://openalex.org/W7166806257","https://openalex.org/W60856060","https://openalex.org/W4411119136","https://openalex.org/W7224172669","https://openalex.org/W7131787953","https://openalex.org/W7224289400","https://openalex.org/W7166799908","https://openalex.org/W4402671633"],"abstract_inverted_index":{"Current":[0],"evaluations":[1],"often":[2],"treat":[3],"Chinese":[4,129],"varieties":[5],"as":[6,110],"monolithic,":[7],"obscuring":[8],"failures":[9],"for":[10,19,69],"regional":[11,20,136],"users.We":[12],"introduce":[13],"RegioZH,":[14],"a":[15,56,95,111],"2,607item":[16],"multiple-choice":[17],"benchmark":[18],"lexical":[21,108],"reasoning":[22],"across":[23,135],"Mainland":[24],"China,":[25],"Taiwan,":[26],"Hong":[27],"Kong,":[28],"Singapore,":[29],"and":[30,35,45,63,65,91,100,106,122],"Malaysia.Built":[31],"by":[32],"region-specific":[33],"annotators":[34],"expertvalidated,":[36],"it":[37],"targets":[38],"localized":[39,107],"idioms,":[40],"slang,":[41],"code-mixing,":[42],"politeness":[43],"conventions,":[44],"sociocultural":[46,119],"expressions.Zero-shot":[47],"results":[48],"on":[49],"eleven":[50],"LLMs":[51],"show":[52,94],"large":[53],"disparities,":[54],"including":[55],"29.4-point":[57],"average":[58],"accuracy":[59],"gap":[60],"between":[61,97],"Taiwan":[62],"Singapore.Persona":[64],"structured":[66],"chain-of-thought":[67],"prompts":[68],"five":[70],"models":[71],"yield":[72],"selective":[73],"gains,":[74],"suggesting":[75],"that":[76,127],"some":[77],"errors":[78],"stem":[79],"from":[80],"retrieval":[81],"or":[82],"framing":[83],"rather":[84],"than":[85],"only":[86],"missing":[87],"knowledge.Representation,":[88],"attention,":[89],"calibration,":[90],"surface-feature":[92],"analyses":[93],"dissociation":[96],"marker":[98],"attention":[99],"semantic":[101,124],"grounding,":[102],"overconfident":[103],"forced-choice":[104],"errors,":[105],"density":[109],"consistent":[112],"difficulty":[113],"predictor.Qualitative":[114],"analysis":[115],"finds":[116],"terminology":[117],"misunderstandings,":[118],"inference":[120],"gaps,":[121],"cross-regional":[123],"divergence.RegioZH":[125],"demonstrates":[126],"apparent":[128],"proficiency":[130],"can":[131],"mask":[132],"uneven":[133],"understanding":[134],"varieties,":[137],"motivating":[138],"intra-language":[139],"robustness":[140],"evaluation":[141],"alongside":[142],"multilingual":[143],"generalization.":[144]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}
