<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2025-m2">
    <titleInfo>
        <title>M²-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mingyang</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lingyu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sophia</namePart>
        <namePart type="family">Horng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maximillian</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kung-Hsiang</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shih-Fu</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Tabular data is used to store information in many real-world systems ranging from finance to healthcare. However, such structured data is often communicated to humans in visually interpretable formats (e.g. charts and textual paragraphs), making it imperative that fact-checking models should be able to reason over multiple pieces of structured evidence presented across different modalities. In this paper, we propose Multi-Document Multi-Modal Table-based Fact Verification (M²-TabFact), a challenging fact verification task that requires jointly reasoning over visual and textual representations of structured data. We design an automatic data generation pipeline that converts existing tabular data into descriptive visual and textual evidence. We then use Large Language Models to generate complex claims that depend on multi-document, multi-modal evidence. In total, we create 8,856 pairs of complex claims and multi-modal evidence through this procedure and systematically evaluate M²-TabFact with a set of strong vision-language models (VLM). We find that existing VLMs have large gaps in fact verification performance compared to humans. Moreover, we find that they are imbalanced when it comes to their ability to handle reason about different modalities, and currently struggle to reason about information extracted from multiple documents.</abstract>
    <identifier type="citekey">zhou-etal-2025-m2</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1345</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1345/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>26239</start>
            <end>26256</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T M²-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data
%A Zhou, Mingyang
%A Zhang, Lingyu
%A Horng, Sophia
%A Chen, Maximillian
%A Huang, Kung-Hsiang
%A Chang, Shih-Fu
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhou-etal-2025-m2
%X Tabular data is used to store information in many real-world systems ranging from finance to healthcare. However, such structured data is often communicated to humans in visually interpretable formats (e.g. charts and textual paragraphs), making it imperative that fact-checking models should be able to reason over multiple pieces of structured evidence presented across different modalities. In this paper, we propose Multi-Document Multi-Modal Table-based Fact Verification (M²-TabFact), a challenging fact verification task that requires jointly reasoning over visual and textual representations of structured data. We design an automatic data generation pipeline that converts existing tabular data into descriptive visual and textual evidence. We then use Large Language Models to generate complex claims that depend on multi-document, multi-modal evidence. In total, we create 8,856 pairs of complex claims and multi-modal evidence through this procedure and systematically evaluate M²-TabFact with a set of strong vision-language models (VLM). We find that existing VLMs have large gaps in fact verification performance compared to humans. Moreover, we find that they are imbalanced when it comes to their ability to handle reason about different modalities, and currently struggle to reason about information extracted from multiple documents.
%R 10.18653/v1/2025.findings-acl.1345
%U https://aclanthology.org/2025.findings-acl.1345/
%U https://doi.org/10.18653/v1/2025.findings-acl.1345
%P 26239-26256

Markdown (Informal)

[M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data](https://aclanthology.org/2025.findings-acl.1345/) (Zhou et al., Findings 2025)

• M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data (Zhou et al., Findings 2025)

ACL

• Mingyang Zhou, Lingyu Zhang, Sophia Horng, Maximillian Chen, Kung-Hsiang Huang, and Shih-Fu Chang. 2025. M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26239–26256, Vienna, Austria. Association for Computational Linguistics.