@inproceedings{wang-etal-2026-charthal,
title = "{C}hart{H}al: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding",
author = "Wang, Xingqi and
Cui, Yiming and
Yao, Xin and
Wang, Shijin and
Hu, Guoping and
Qin, Xiaoyu",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.88/",
pages = "1779--1796",
ISBN = "979-8-89176-444-6",
abstract = "Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities and demands rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, with even GPT-5 achieving only 34.46{\%} accuracy. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations. We also evaluate several representative hallucination mitigation methods and find that they exhibit notable limitations, which underscores the urgent need for more robust chart-specific mitigation strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-charthal">
<titleInfo>
<title>ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Qin</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>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</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">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities and demands rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, with even GPT-5 achieving only 34.46% accuracy. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations. We also evaluate several representative hallucination mitigation methods and find that they exhibit notable limitations, which underscores the urgent need for more robust chart-specific mitigation strategies.</abstract>
<identifier type="citekey">wang-etal-2026-charthal</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.88/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1779</start>
<end>1796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
%A Wang, Xingqi
%A Cui, Yiming
%A Yao, Xin
%A Wang, Shijin
%A Hu, Guoping
%A Qin, Xiaoyu
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wang-etal-2026-charthal
%X Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities and demands rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, with even GPT-5 achieving only 34.46% accuracy. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations. We also evaluate several representative hallucination mitigation methods and find that they exhibit notable limitations, which underscores the urgent need for more robust chart-specific mitigation strategies.
%U https://aclanthology.org/2026.findings-aacl.88/
%P 1779-1796
Markdown (Informal)
[ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding](https://aclanthology.org/2026.findings-aacl.88/) (Wang et al., Findings 2026)
ACL