@inproceedings{zheng-etal-2026-regiozh,
title = "{R}egio{ZH}: Unveiling Comprehension Disparities across Regional {C}hinese Varieties in {LLM}s",
author = "Zheng, Weihua and
Kui, Wu and
Doan, Thong T. and
Jingxia, Lin and
Aw, AiTi and
Chen, Nancy F. and
Lee, Roy Ka-Wei",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.793/",
pages = "16774--16811",
ISBN = "979-8-89176-462-0",
abstract = "Current evaluations often treat Chinese varieties as monolithic, obscuring failures for regional users. We introduce RegioZH, a 2,607-item multiple-choice benchmark for regional lexical reasoning across Mainland China, Taiwan, Hong Kong, Singapore, and Malaysia. Built by region-specific annotators and expert-validated, it targets localized idioms, slang, code-mixing, politeness conventions, and sociocultural expressions. Zero-shot results on eleven LLMs show large disparities, including a 29.4-point average accuracy gap between Taiwan and Singapore. Persona and structured chain-of-thought prompts for five models yield selective gains, suggesting that some errors stem from retrieval or framing rather than only missing knowledge. Representation, attention, calibration, and surface-feature analyses show a dissociation between marker attention and semantic grounding, overconfident forced-choice errors, and localized lexical density as a consistent difficulty predictor. Qualitative analysis finds terminology misunderstandings, sociocultural inference gaps, and cross-regional semantic divergence. RegioZH demonstrates that apparent Chinese proficiency can mask uneven understanding across regional varieties, motivating intra-language robustness evaluation alongside multilingual generalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2026-regiozh">
<titleInfo>
<title>RegioZH: Unveiling Comprehension Disparities across Regional Chinese Varieties in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wu</namePart>
<namePart type="family">Kui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thong</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Jingxia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AiTi</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roy</namePart>
<namePart type="given">Ka-Wei</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Current evaluations often treat Chinese varieties as monolithic, obscuring failures for regional users. We introduce RegioZH, a 2,607-item multiple-choice benchmark for regional lexical reasoning across Mainland China, Taiwan, Hong Kong, Singapore, and Malaysia. Built by region-specific annotators and expert-validated, it targets localized idioms, slang, code-mixing, politeness conventions, and sociocultural expressions. Zero-shot results on eleven LLMs show large disparities, including a 29.4-point average accuracy gap between Taiwan and Singapore. Persona and structured chain-of-thought prompts for five models yield selective gains, suggesting that some errors stem from retrieval or framing rather than only missing knowledge. Representation, attention, calibration, and surface-feature analyses show a dissociation between marker attention and semantic grounding, overconfident forced-choice errors, and localized lexical density as a consistent difficulty predictor. Qualitative analysis finds terminology misunderstandings, sociocultural inference gaps, and cross-regional semantic divergence. RegioZH demonstrates that apparent Chinese proficiency can mask uneven understanding across regional varieties, motivating intra-language robustness evaluation alongside multilingual generalization.</abstract>
<identifier type="citekey">zheng-etal-2026-regiozh</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.793/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>16774</start>
<end>16811</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RegioZH: Unveiling Comprehension Disparities across Regional Chinese Varieties in LLMs
%A Zheng, Weihua
%A Kui, Wu
%A Doan, Thong T.
%A Jingxia, Lin
%A Aw, AiTi
%A Chen, Nancy F.
%A Lee, Roy Ka-Wei
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zheng-etal-2026-regiozh
%X Current evaluations often treat Chinese varieties as monolithic, obscuring failures for regional users. We introduce RegioZH, a 2,607-item multiple-choice benchmark for regional lexical reasoning across Mainland China, Taiwan, Hong Kong, Singapore, and Malaysia. Built by region-specific annotators and expert-validated, it targets localized idioms, slang, code-mixing, politeness conventions, and sociocultural expressions. Zero-shot results on eleven LLMs show large disparities, including a 29.4-point average accuracy gap between Taiwan and Singapore. Persona and structured chain-of-thought prompts for five models yield selective gains, suggesting that some errors stem from retrieval or framing rather than only missing knowledge. Representation, attention, calibration, and surface-feature analyses show a dissociation between marker attention and semantic grounding, overconfident forced-choice errors, and localized lexical density as a consistent difficulty predictor. Qualitative analysis finds terminology misunderstandings, sociocultural inference gaps, and cross-regional semantic divergence. RegioZH demonstrates that apparent Chinese proficiency can mask uneven understanding across regional varieties, motivating intra-language robustness evaluation alongside multilingual generalization.
%U https://aclanthology.org/2026.findings-emnlp.793/
%P 16774-16811
Markdown (Informal)
[RegioZH: Unveiling Comprehension Disparities across Regional Chinese Varieties in LLMs](https://aclanthology.org/2026.findings-emnlp.793/) (Zheng et al., Findings 2026)
ACL