@inproceedings{tam-etal-2026-vistw,
title = "{V}is{TW}: Benchmarking Vision-Language Models for {T}aiwanese {M}andarin in {T}aiwan",
author = "Tam, Zhi Rui and
Shih, Yung-Yu and
Lee, Yen-Wei and
Pai, Ya-Ting and
Chang, Wen Yu and
Chen, Yun-Nung",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1830/",
pages = "36711--36756",
ISBN = "979-8-89176-395-1",
abstract = "Vision-Language Models (VLMs) often struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context. We introduce VisTW, a comprehensive benchmark featuring (i) multiple-choice questions (3,795 academic questions) and (ii) free-form generation evaluation (141 Taiwanese-context free-form pairs). Beyond standard accuracy, we investigate character mixing{---} the unintended production of Simplified Chinese characters under Taiwanese-Mandarin-style prompts{---}and propose a human-grounded purity penalty derived from perceptual thresholds measured from users. Our evaluation reveals substantial character contamination (3{\%}{--}19{\%}) across state-of-the-art VLMs. We find that Gemini-3-Pro significantly outperforms the strongest open-weight baseline, Qwen3 235B MoE, by up to 22 percentage points on dialogue tasks once the purity penalty is applied. These results highlight orthographic consistency as a vital, yet overlooked, dimension for localized multimodal evaluation and deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tam-etal-2026-vistw">
<titleInfo>
<title>VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="given">Rui</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yung-Yu</namePart>
<namePart type="family">Shih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen-Wei</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ya-Ting</namePart>
<namePart type="family">Pai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="given">Yu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Vision-Language Models (VLMs) often struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context. We introduce VisTW, a comprehensive benchmark featuring (i) multiple-choice questions (3,795 academic questions) and (ii) free-form generation evaluation (141 Taiwanese-context free-form pairs). Beyond standard accuracy, we investigate character mixing— the unintended production of Simplified Chinese characters under Taiwanese-Mandarin-style prompts—and propose a human-grounded purity penalty derived from perceptual thresholds measured from users. Our evaluation reveals substantial character contamination (3%–19%) across state-of-the-art VLMs. We find that Gemini-3-Pro significantly outperforms the strongest open-weight baseline, Qwen3 235B MoE, by up to 22 percentage points on dialogue tasks once the purity penalty is applied. These results highlight orthographic consistency as a vital, yet overlooked, dimension for localized multimodal evaluation and deployment.</abstract>
<identifier type="citekey">tam-etal-2026-vistw</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1830/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36711</start>
<end>36756</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan
%A Tam, Zhi Rui
%A Shih, Yung-Yu
%A Lee, Yen-Wei
%A Pai, Ya-Ting
%A Chang, Wen Yu
%A Chen, Yun-Nung
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F tam-etal-2026-vistw
%X Vision-Language Models (VLMs) often struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context. We introduce VisTW, a comprehensive benchmark featuring (i) multiple-choice questions (3,795 academic questions) and (ii) free-form generation evaluation (141 Taiwanese-context free-form pairs). Beyond standard accuracy, we investigate character mixing— the unintended production of Simplified Chinese characters under Taiwanese-Mandarin-style prompts—and propose a human-grounded purity penalty derived from perceptual thresholds measured from users. Our evaluation reveals substantial character contamination (3%–19%) across state-of-the-art VLMs. We find that Gemini-3-Pro significantly outperforms the strongest open-weight baseline, Qwen3 235B MoE, by up to 22 percentage points on dialogue tasks once the purity penalty is applied. These results highlight orthographic consistency as a vital, yet overlooked, dimension for localized multimodal evaluation and deployment.
%U https://aclanthology.org/2026.findings-acl.1830/
%P 36711-36756
Markdown (Informal)
[VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan](https://aclanthology.org/2026.findings-acl.1830/) (Tam et al., Findings 2026)
ACL