@inproceedings{tonglet-etal-2026-protecting,
title = "Protecting multimodal large language models against misleading visualizations",
author = "Tonglet, Jonathan and
Tuytelaars, Tinne and
Moens, Marie-Francine and
Gurevych, Iryna",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.377/",
pages = "8329--8349",
ISBN = "979-8-89176-390-6",
abstract = "Visualizations play a pivotal role in daily communication in an increasingly data-driven world. Research on multimodal large language models (MLLMs) for automated chart understanding has accelerated massively, with steady improvements on standard benchmarks. However, for MLLMs to be reliable, they must be robust to misleading visualizations, i.e., charts that distort the underlying data, leading readers to draw inaccurate conclusions. Here, we uncover an important vulnerability: MLLM question-answering (QA) accuracy on misleading visualizations drops on average to the level of the random baseline. To address this, we provide the first comparison of six inference-time methods to improve QA performance on misleading visualizations, without compromising accuracy on non-misleading ones. We find that two methods, table-based QA and redrawing the visualization, are effective, with improvements of up to 19.6 percentage points. We make our code and data available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tonglet-etal-2026-protecting">
<titleInfo>
<title>Protecting multimodal large language models against misleading visualizations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Tonglet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tinne</namePart>
<namePart type="family">Tuytelaars</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Visualizations play a pivotal role in daily communication in an increasingly data-driven world. Research on multimodal large language models (MLLMs) for automated chart understanding has accelerated massively, with steady improvements on standard benchmarks. However, for MLLMs to be reliable, they must be robust to misleading visualizations, i.e., charts that distort the underlying data, leading readers to draw inaccurate conclusions. Here, we uncover an important vulnerability: MLLM question-answering (QA) accuracy on misleading visualizations drops on average to the level of the random baseline. To address this, we provide the first comparison of six inference-time methods to improve QA performance on misleading visualizations, without compromising accuracy on non-misleading ones. We find that two methods, table-based QA and redrawing the visualization, are effective, with improvements of up to 19.6 percentage points. We make our code and data available.</abstract>
<identifier type="citekey">tonglet-etal-2026-protecting</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.377/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>8329</start>
<end>8349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Protecting multimodal large language models against misleading visualizations
%A Tonglet, Jonathan
%A Tuytelaars, Tinne
%A Moens, Marie-Francine
%A Gurevych, Iryna
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F tonglet-etal-2026-protecting
%X Visualizations play a pivotal role in daily communication in an increasingly data-driven world. Research on multimodal large language models (MLLMs) for automated chart understanding has accelerated massively, with steady improvements on standard benchmarks. However, for MLLMs to be reliable, they must be robust to misleading visualizations, i.e., charts that distort the underlying data, leading readers to draw inaccurate conclusions. Here, we uncover an important vulnerability: MLLM question-answering (QA) accuracy on misleading visualizations drops on average to the level of the random baseline. To address this, we provide the first comparison of six inference-time methods to improve QA performance on misleading visualizations, without compromising accuracy on non-misleading ones. We find that two methods, table-based QA and redrawing the visualization, are effective, with improvements of up to 19.6 percentage points. We make our code and data available.
%U https://aclanthology.org/2026.acl-long.377/
%P 8329-8349
Markdown (Informal)
[Protecting multimodal large language models against misleading visualizations](https://aclanthology.org/2026.acl-long.377/) (Tonglet et al., ACL 2026)
ACL