@inproceedings{truong-etal-2026-charttablevivqa,
title = "{C}hart{T}able{V}i{VQA}: A {V}ietnamese Benchmark Dataset for Visual Question Answering with Reasoning Instruction over Charts and Tables Images",
author = "Truong, Quang Nhat and
Thang, Pham Quoc and
Luu, Son T.",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.5/",
pages = "99--123",
ISBN = "979-8-89176-439-2",
abstract = "Visual Question Answering (VQA) over charts and tables requires joint reasoning over language, visual structure, and numerical information, yet no standard benchmark currently exists for Vietnamese. We introduce \textbf{ChartTableViVQA}, a Vietnamese VQA dataset with 13,003 question{--}answer{--}instruction triplets over 868 chart and table images. Questions cover multiple reasoning types, ranging from simple value lookup to multi-step aggregation, comparison, and trend analysis, and are accompanied by concise instructions that explicitly guide the reasoning process. The dataset is built via a semi-automatic human-in-the-loop pipeline, combining large language model generation with manual verification by Vietnamese annotators. We evaluate several vision-language models in zero-shot and instruction-based settings. Results show strong performance on simple questions but clear weaknesses in complex reasoning, particularly on charts, while instruction-based prompting consistently improves accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="truong-etal-2026-charttablevivqa">
<titleInfo>
<title>ChartTableViVQA: A Vietnamese Benchmark Dataset for Visual Question Answering with Reasoning Instruction over Charts and Tables Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quang</namePart>
<namePart type="given">Nhat</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pham</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Thang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Son</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Visual Question Answering (VQA) over charts and tables requires joint reasoning over language, visual structure, and numerical information, yet no standard benchmark currently exists for Vietnamese. We introduce ChartTableViVQA, a Vietnamese VQA dataset with 13,003 question–answer–instruction triplets over 868 chart and table images. Questions cover multiple reasoning types, ranging from simple value lookup to multi-step aggregation, comparison, and trend analysis, and are accompanied by concise instructions that explicitly guide the reasoning process. The dataset is built via a semi-automatic human-in-the-loop pipeline, combining large language model generation with manual verification by Vietnamese annotators. We evaluate several vision-language models in zero-shot and instruction-based settings. Results show strong performance on simple questions but clear weaknesses in complex reasoning, particularly on charts, while instruction-based prompting consistently improves accuracy.</abstract>
<identifier type="citekey">truong-etal-2026-charttablevivqa</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.5/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>99</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChartTableViVQA: A Vietnamese Benchmark Dataset for Visual Question Answering with Reasoning Instruction over Charts and Tables Images
%A Truong, Quang Nhat
%A Thang, Pham Quoc
%A Luu, Son T.
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F truong-etal-2026-charttablevivqa
%X Visual Question Answering (VQA) over charts and tables requires joint reasoning over language, visual structure, and numerical information, yet no standard benchmark currently exists for Vietnamese. We introduce ChartTableViVQA, a Vietnamese VQA dataset with 13,003 question–answer–instruction triplets over 868 chart and table images. Questions cover multiple reasoning types, ranging from simple value lookup to multi-step aggregation, comparison, and trend analysis, and are accompanied by concise instructions that explicitly guide the reasoning process. The dataset is built via a semi-automatic human-in-the-loop pipeline, combining large language model generation with manual verification by Vietnamese annotators. We evaluate several vision-language models in zero-shot and instruction-based settings. Results show strong performance on simple questions but clear weaknesses in complex reasoning, particularly on charts, while instruction-based prompting consistently improves accuracy.
%U https://aclanthology.org/2026.aacl-long.5/
%P 99-123
Markdown (Informal)
[ChartTableViVQA: A Vietnamese Benchmark Dataset for Visual Question Answering with Reasoning Instruction over Charts and Tables Images](https://aclanthology.org/2026.aacl-long.5/) (Truong et al., AACL-IJCNLP 2026)
ACL