<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wen-etal-2026-trivtab">
    <titleInfo>
        <title>TriVTab: Fusing Triple-Based Structured Reasoning and Visual Reasoning for Multimodal Table Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhuo</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weifan</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ji</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multimodal Table Question Answering requires both accurate perception of cell contents in a table image and precise symbolic reasoning over the extracted values; multimodal large language models (MLLMs) handle the former well, but the latter remains more challenging, motivating the use of an explicit code interpreter for computation. Through a fine-grained partition analysis, we find instance-level complementarity between the two paths: even when the visual path is stronger overall, the structured path correctly answers a non-trivial subset of questions missed by the visual path. To exploit this complementarity, we propose TriVTab, a dual-path framework that combines direct visual reasoning with triple-based structured reasoning through agreement-gated multimodal fusion. Rather than seeking a uniformly stronger standalone path, TriVTab reconciles complementary paths to improve a strong visual baseline. TriVTab (i) uses an execution-oriented cell-triple representation to bind each value to an explicit row and column context, making complex table structures directly addressable for code generation; and (ii) employs agreement-gated multimodal fusion to treat cross-path agreement as corroboration and concentrate multimodal fusion on divergent predictions. On five multimodal Table QA benchmarks, TriVTab improves over a strong Qwen3-VL-8B chain-of-thought baseline by +2.53 points on average and over a Self-Reflection baseline by +3.46 points.</abstract>
    <identifier type="citekey">wen-etal-2026-trivtab</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2568/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>58334</start>
            <end>58354</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TriVTab: Fusing Triple-Based Structured Reasoning and Visual Reasoning for Multimodal Table Question Answering
%A Wen, Zhuo
%A Lin, Yang
%A Zhao, Weifan
%A Zhang, Ji
%A Gao, Jun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wen-etal-2026-trivtab
%X Multimodal Table Question Answering requires both accurate perception of cell contents in a table image and precise symbolic reasoning over the extracted values; multimodal large language models (MLLMs) handle the former well, but the latter remains more challenging, motivating the use of an explicit code interpreter for computation. Through a fine-grained partition analysis, we find instance-level complementarity between the two paths: even when the visual path is stronger overall, the structured path correctly answers a non-trivial subset of questions missed by the visual path. To exploit this complementarity, we propose TriVTab, a dual-path framework that combines direct visual reasoning with triple-based structured reasoning through agreement-gated multimodal fusion. Rather than seeking a uniformly stronger standalone path, TriVTab reconciles complementary paths to improve a strong visual baseline. TriVTab (i) uses an execution-oriented cell-triple representation to bind each value to an explicit row and column context, making complex table structures directly addressable for code generation; and (ii) employs agreement-gated multimodal fusion to treat cross-path agreement as corroboration and concentrate multimodal fusion on divergent predictions. On five multimodal Table QA benchmarks, TriVTab improves over a strong Qwen3-VL-8B chain-of-thought baseline by +2.53 points on average and over a Self-Reflection baseline by +3.46 points.
%U https://aclanthology.org/2026.emnlp-main.2568/
%P 58334-58354

Markdown (Informal)

[TriVTab: Fusing Triple-Based Structured Reasoning and Visual Reasoning for Multimodal Table Question Answering](https://aclanthology.org/2026.emnlp-main.2568/) (Wen et al., EMNLP 2026)

• TriVTab: Fusing Triple-Based Structured Reasoning and Visual Reasoning for Multimodal Table Question Answering (Wen et al., EMNLP 2026)

ACL

• Zhuo Wen, Yang Lin, Weifan Zhao, Ji Zhang, and Jun Gao. 2026. TriVTab: Fusing Triple-Based Structured Reasoning and Visual Reasoning for Multimodal Table Question Answering. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 58334–58354, Budapest, Hungary. Association for Computational Linguistics.