<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-trace">
    <titleInfo>
        <title>TRACE: Tree-Structured Reasoning for Multi-Table Multi-Hop Fact-Checking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Senyi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dongwon</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Delvin</namePart>
        <namePart type="given">Ce</namePart>
        <namePart type="family">Zhang</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>Multi-table fact-checking verifies claims whose evidence is distributed across multiple tables and connected through multi-hop reasoning. This setting is challenging because claims may contain chained or nested dependencies, table retrieval is noisy, and retrieved evidence must be selected and composed before a final verdict can be made. We introduce two multi-table fact verification testbeds, OTT-FV and Hybrid-FV, and propose TRACE, a tree-structured framework that connects claim decomposition, evidence retrieval, and evidence composition. TRACE represents each claim as a dependency-aware semantic tree, retrieves locally relevant table evidence for each node, and composes evidence-aware node representations bottom-up to produce the final verdict. Experiments on TabFact, OTT-FV, and Hybrid-FV show that TRACE consistently improves over strong baselines across multiple backbones under both gold- and open-evidence settings. Further analyses show that tree construction, node-level retrieval, and bottom-up evidence composition all contribute to multi-table verification.</abstract>
    <identifier type="citekey">zhang-etal-2026-trace</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.968/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>22324</start>
            <end>22342</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRACE: Tree-Structured Reasoning for Multi-Table Multi-Hop Fact-Checking
%A Zhang, Senyi
%A Lee, Dongwon
%A Zhang, Delvin Ce
%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 zhang-etal-2026-trace
%X Multi-table fact-checking verifies claims whose evidence is distributed across multiple tables and connected through multi-hop reasoning. This setting is challenging because claims may contain chained or nested dependencies, table retrieval is noisy, and retrieved evidence must be selected and composed before a final verdict can be made. We introduce two multi-table fact verification testbeds, OTT-FV and Hybrid-FV, and propose TRACE, a tree-structured framework that connects claim decomposition, evidence retrieval, and evidence composition. TRACE represents each claim as a dependency-aware semantic tree, retrieves locally relevant table evidence for each node, and composes evidence-aware node representations bottom-up to produce the final verdict. Experiments on TabFact, OTT-FV, and Hybrid-FV show that TRACE consistently improves over strong baselines across multiple backbones under both gold- and open-evidence settings. Further analyses show that tree construction, node-level retrieval, and bottom-up evidence composition all contribute to multi-table verification.
%U https://aclanthology.org/2026.emnlp-main.968/
%P 22324-22342

Markdown (Informal)

[TRACE: Tree-Structured Reasoning for Multi-Table Multi-Hop Fact-Checking](https://aclanthology.org/2026.emnlp-main.968/) (Zhang et al., EMNLP 2026)

• TRACE: Tree-Structured Reasoning for Multi-Table Multi-Hop Fact-Checking (Zhang et al., EMNLP 2026)

ACL

• Senyi Zhang, Dongwon Lee, and Delvin Ce Zhang. 2026. TRACE: Tree-Structured Reasoning for Multi-Table Multi-Hop Fact-Checking. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 22324–22342, Budapest, Hungary. Association for Computational Linguistics.