<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ungureanu-etal-2026-ensembling">
    <titleInfo>
        <title>Ensembling Elicitation Strategies for Knowledge Base Construction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vlad-Mădălin</namePart>
        <namePart type="family">Ungureanu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matei</namePart>
        <namePart type="family">Neacșu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ianis</namePart>
        <namePart type="family">Belu</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>Large language models represent a promising alternative for automating structured knowledge bases construction, but their reliance on parametric knowledge makes them susceptible to hallucinations and incomplete information. The Automated Knowledge Base Construction competition investigates the use of large language models to construct structured knowledge bases from their parametric knowledge alone, without fine-tuning or external retrieval. Given a subject–relation pair, participants must predict the complete set of correct objects across several relation types. Our approach proposes an ensemble of four prompting strategies: question-style, masked-style, few-shot chain-of-thought, and least-to-most prompting. It aggregates their predictions using relation-aware majority voting. The resulting system achieves a Macro-F1 of 0.6651 on the test set, substantially outperforming the provided baseline of 0.294.</abstract>
    <identifier type="citekey">ungureanu-etal-2026-ensembling</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.43/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>543</start>
            <end>549</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Ensembling Elicitation Strategies for Knowledge Base Construction
%A Ungureanu, Vlad-Mădălin
%A Neacșu, Matei
%A Belu, Ianis
%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 ungureanu-etal-2026-ensembling
%X Large language models represent a promising alternative for automating structured knowledge bases construction, but their reliance on parametric knowledge makes them susceptible to hallucinations and incomplete information. The Automated Knowledge Base Construction competition investigates the use of large language models to construct structured knowledge bases from their parametric knowledge alone, without fine-tuning or external retrieval. Given a subject–relation pair, participants must predict the complete set of correct objects across several relation types. Our approach proposes an ensemble of four prompting strategies: question-style, masked-style, few-shot chain-of-thought, and least-to-most prompting. It aggregates their predictions using relation-aware majority voting. The resulting system achieves a Macro-F1 of 0.6651 on the test set, substantially outperforming the provided baseline of 0.294.
%U https://aclanthology.org/2026.akbc-1.43/
%P 543-549

Markdown (Informal)

[Ensembling Elicitation Strategies for Knowledge Base Construction](https://aclanthology.org/2026.akbc-1.43/) (Ungureanu et al., AKBC 2026)

• Ensembling Elicitation Strategies for Knowledge Base Construction (Ungureanu et al., AKBC 2026)

ACL

• Vlad-Mădălin Ungureanu, Matei Neacșu, and Ianis Belu. 2026. Ensembling Elicitation Strategies for Knowledge Base Construction. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 543–549, Budapest, Hungary. Association for Computational Linguistics.