@inproceedings{lee-etal-2026-visdot,
title = "{V}is{D}o{T} : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought",
author = "Lee, Eunsoo and
Lee, Jeongwoo and
Hong, Minki and
Choi, Jangho and
Kim, Jihie",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.30/",
pages = "610--640",
ISBN = "979-8-89176-386-9",
abstract = "Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual grounding constitutes a major bottleneck for chart-based reasoning. We propose VisDoT, a framework that enhances visual reasoning through human-like interpretation grounding. We formalize four perceptual tasks based on the theory of graphical perception such as position and length. Building on this foundation, we introduce decomposition-of-thought (DoT) prompting, which sequentially separates questions into visual perception sub-questions and logic sub-questions. Fine-tuning InternVL with VisDoT achieves a +11.2{\%} improvement on ChartQA and surpasses GPT-4o on the more challenging ChartQAPro benchmark. On the newly introduced VisDoTQA benchmark, the model improves by +33.2{\%}. Furthermore, consistent zero-shot gains on diverse open-domain VQA benchmarks confirm the generalizability of the perception-logic separation strategy for visual question answering in general. VisDoT leverages human-like perception to enhance visual grounding, achieving state-of-the-art chart understanding and interpretable visual reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-visdot">
<titleInfo>
<title>VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunsoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeongwoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minki</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jangho</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihie</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual grounding constitutes a major bottleneck for chart-based reasoning. We propose VisDoT, a framework that enhances visual reasoning through human-like interpretation grounding. We formalize four perceptual tasks based on the theory of graphical perception such as position and length. Building on this foundation, we introduce decomposition-of-thought (DoT) prompting, which sequentially separates questions into visual perception sub-questions and logic sub-questions. Fine-tuning InternVL with VisDoT achieves a +11.2% improvement on ChartQA and surpasses GPT-4o on the more challenging ChartQAPro benchmark. On the newly introduced VisDoTQA benchmark, the model improves by +33.2%. Furthermore, consistent zero-shot gains on diverse open-domain VQA benchmarks confirm the generalizability of the perception-logic separation strategy for visual question answering in general. VisDoT leverages human-like perception to enhance visual grounding, achieving state-of-the-art chart understanding and interpretable visual reasoning.</abstract>
<identifier type="citekey">lee-etal-2026-visdot</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.30/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>610</start>
<end>640</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought
%A Lee, Eunsoo
%A Lee, Jeongwoo
%A Hong, Minki
%A Choi, Jangho
%A Kim, Jihie
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F lee-etal-2026-visdot
%X Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual grounding constitutes a major bottleneck for chart-based reasoning. We propose VisDoT, a framework that enhances visual reasoning through human-like interpretation grounding. We formalize four perceptual tasks based on the theory of graphical perception such as position and length. Building on this foundation, we introduce decomposition-of-thought (DoT) prompting, which sequentially separates questions into visual perception sub-questions and logic sub-questions. Fine-tuning InternVL with VisDoT achieves a +11.2% improvement on ChartQA and surpasses GPT-4o on the more challenging ChartQAPro benchmark. On the newly introduced VisDoTQA benchmark, the model improves by +33.2%. Furthermore, consistent zero-shot gains on diverse open-domain VQA benchmarks confirm the generalizability of the perception-logic separation strategy for visual question answering in general. VisDoT leverages human-like perception to enhance visual grounding, achieving state-of-the-art chart understanding and interpretable visual reasoning.
%U https://aclanthology.org/2026.findings-eacl.30/
%P 610-640
Markdown (Informal)
[VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought](https://aclanthology.org/2026.findings-eacl.30/) (Lee et al., Findings 2026)
ACL