<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cha-etal-2026-trace">
    <titleInfo>
        <title>TRACE: Table–Text Relationalization and Completion of Evidence for Coverage-Sensitive QA</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sunho</namePart>
        <namePart type="family">Cha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungho</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wook-Shin</namePart>
        <namePart type="family">Han</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>Table–Text question answering asks systems to answer natural-language questions whose evidence is split between structured tables and linked unstructured passages. Many realistic questions in this setting are coverage-sensitive: the answer depends on a set of evidence items distributed across table rows and linked passages, and the same failure mode that appears in aggregation also surfaces in joins, multi-row filters, list questions, and universal or existential queries. Existing hybrid systems retrieve and read such evidence, yet leave passage-derived facts as strings in the LLM context rather than as typed, joinable, and repairable relational values that SQL can operate on. We propose TRACE (Table–Text Relationalization And Completion of Evidence), a completeness-aware query-processing framework built on two relational state transformations. Schema-Guided Relationalization (SGR) turns linked passages into typed, foreign-keyed side tables, exposing textual evidence as SQL-visible relational values; Question-Conditioned Relational Completion (QCRC) then repairs this state per question by adding missing attributes and filling incomplete cells. SQL performs set-oriented operations over the completed state, while a lightweight passage fallback handles residual gaps. On the coverage-sensitive SPARTA benchmark, TRACE more than triples the strongest baseline F1 (60.5 vs. 19.2 with gpt-4o-mini); on lookup-heavy HYBRIDQA, it stays competitive while substantially reducing the drop on questions that require many evidence items.</abstract>
    <identifier type="citekey">cha-etal-2026-trace</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2594/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>58907</start>
            <end>58926</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRACE: Table–Text Relationalization and Completion of Evidence for Coverage-Sensitive QA
%A Cha, Sunho
%A Park, Sungho
%A Han, Wook-Shin
%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 cha-etal-2026-trace
%X Table–Text question answering asks systems to answer natural-language questions whose evidence is split between structured tables and linked unstructured passages. Many realistic questions in this setting are coverage-sensitive: the answer depends on a set of evidence items distributed across table rows and linked passages, and the same failure mode that appears in aggregation also surfaces in joins, multi-row filters, list questions, and universal or existential queries. Existing hybrid systems retrieve and read such evidence, yet leave passage-derived facts as strings in the LLM context rather than as typed, joinable, and repairable relational values that SQL can operate on. We propose TRACE (Table–Text Relationalization And Completion of Evidence), a completeness-aware query-processing framework built on two relational state transformations. Schema-Guided Relationalization (SGR) turns linked passages into typed, foreign-keyed side tables, exposing textual evidence as SQL-visible relational values; Question-Conditioned Relational Completion (QCRC) then repairs this state per question by adding missing attributes and filling incomplete cells. SQL performs set-oriented operations over the completed state, while a lightweight passage fallback handles residual gaps. On the coverage-sensitive SPARTA benchmark, TRACE more than triples the strongest baseline F1 (60.5 vs. 19.2 with gpt-4o-mini); on lookup-heavy HYBRIDQA, it stays competitive while substantially reducing the drop on questions that require many evidence items.
%U https://aclanthology.org/2026.emnlp-main.2594/
%P 58907-58926

Markdown (Informal)

[TRACE: Table–Text Relationalization and Completion of Evidence for Coverage-Sensitive QA](https://aclanthology.org/2026.emnlp-main.2594/) (Cha et al., EMNLP 2026)

• TRACE: Table–Text Relationalization and Completion of Evidence for Coverage-Sensitive QA (Cha et al., EMNLP 2026)

ACL

• Sunho Cha, Sungho Park, and Wook-Shin Han. 2026. TRACE: Table–Text Relationalization and Completion of Evidence for Coverage-Sensitive QA. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 58907–58926, Budapest, Hungary. Association for Computational Linguistics.