<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thanga-etal-2026-evidence">
    <titleInfo>
        <title>Evidence-Guided Schema Normalization for Temporal Tabular Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ashish</namePart>
        <namePart type="family">Thanga</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vibhu</namePart>
        <namePart type="family">Dixit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhilash</namePart>
        <namePart type="family">Shankarampeta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Gupta</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 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jan-Christoph</namePart>
            <namePart type="family">Kalo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ndapa</namePart>
            <namePart type="family">Nakashole</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Razniewski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabian</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Suchanek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andrew</namePart>
            <namePart type="family">McCallum</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">979-8-89176-464-4</identifier>
    </relatedItem>
    <abstract>Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task as automated knowledge base construction: (1) prompting an LLM to synthesize a 3NF-compliant relational schema from Wikipedia infobox timelines, (2) populating the schema to obtain a queryable database, and (3) generating and executing SQL queries against it, with QA accuracy serving as an extrinsic evaluation of the constructed knowledge base. In a controlled grid of three schema generators crossed with six query models, the schema source accounts for 79.5% of the exact match (EM) variance against 1.6% for the query model: replacing the schema, and the prompt scaffolding derived from it, shifts EM by 14.7 to 20.0 points, whereas replacing the query model under a fixed schema shifts it by 4.4 to 12.1. From this evidence, we distill three candidate schema-design principles: balanced normalization, semantic naming, and consistent temporal anchoring, framed as correlational hypotheses. Our best configuration (Gemini 2.5 Flash schemas + Gemini-2.0-Flash queries) reaches 80.39 EM, 11.5 points above the strongest reported baseline (68.89 EM); an open-weights configuration reaches 79.52.</abstract>
    <identifier type="citekey">thanga-etal-2026-evidence</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.15/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>185</start>
            <end>223</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
%A Thanga, Ashish
%A Dixit, Vibhu
%A Shankarampeta, Abhilash
%A Gupta, Vivek
%Y Kalo, Jan-Christoph
%Y Nakashole, Ndapa
%Y Razniewski, Simon
%Y Suchanek, Fabian M.
%Y Vlachos, Andreas
%Y McCallum, Andrew
%S Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-464-4
%F thanga-etal-2026-evidence
%X Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task as automated knowledge base construction: (1) prompting an LLM to synthesize a 3NF-compliant relational schema from Wikipedia infobox timelines, (2) populating the schema to obtain a queryable database, and (3) generating and executing SQL queries against it, with QA accuracy serving as an extrinsic evaluation of the constructed knowledge base. In a controlled grid of three schema generators crossed with six query models, the schema source accounts for 79.5% of the exact match (EM) variance against 1.6% for the query model: replacing the schema, and the prompt scaffolding derived from it, shifts EM by 14.7 to 20.0 points, whereas replacing the query model under a fixed schema shifts it by 4.4 to 12.1. From this evidence, we distill three candidate schema-design principles: balanced normalization, semantic naming, and consistent temporal anchoring, framed as correlational hypotheses. Our best configuration (Gemini 2.5 Flash schemas + Gemini-2.0-Flash queries) reaches 80.39 EM, 11.5 points above the strongest reported baseline (68.89 EM); an open-weights configuration reaches 79.52.
%U https://aclanthology.org/2026.akbc-1.15/
%P 185-223

Markdown (Informal)

[Evidence-Guided Schema Normalization for Temporal Tabular Reasoning](https://aclanthology.org/2026.akbc-1.15/) (Thanga et al., AKBC 2026)

• Evidence-Guided Schema Normalization for Temporal Tabular Reasoning (Thanga et al., AKBC 2026)

ACL

• Ashish Thanga, Vibhu Dixit, Abhilash Shankarampeta, and Vivek Gupta. 2026. Evidence-Guided Schema Normalization for Temporal Tabular Reasoning. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 185–223, Budapest, Hungary. Association for Computational Linguistics.