<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-forced">
    <titleInfo>
        <title>A Forced Answer Channel for Closed-Book Knowledge Base Construction at LM-KBC 2026</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiqun</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengfei</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lawrence</namePart>
        <namePart type="given">B</namePart>
        <namePart type="family">Hsieh</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>The AKBC 2026 shared task (Kalo et al., 2026) asks a system to complete the object set of a subject and a relation out of a language model’s parameters, with no retrieval, no training, and no more than 32B parameters. Our system drives one 29.6B backbone through three stages. Several elicitation channels per relation build a candidate pool, exhaustive one-token Yes/No probes verify whatever part of the answer space can be enumerated, and a per-relation decision layer emits the object set. The backbone writes a reasoning channel before its user-facing answer, so a probe prompt has to append the answer-channel header before its first generated token is a verdict. Forcing that channel also makes auxiliary generations cheap, which is what puts roughly 26k border probes inside the budget. Most decision constants are fitted on validation gold under a rule that displaces an incumbent only on a strict improvement of more than one row, and the fitting procedure itself is cross-validated, which cut one city gain from +0.070 to +0.020 before it was adopted. The system scores 0.6553 official macro-F1 against 0.6415 for a prompting baseline on the same backbone, and the gap is uneven: the machinery is worth +0.1662 on awards and costs 0.0204 on hasCapacity, where plain prompting wins. We also report the ceiling we could not move. Twenty-one method families have been fitted against hasCapacity and none of them beats a mass vote over the pool. Harvesting the model’s own reasoning traces raises pool coverage from 0.582 to 0.724 and converts none of it.</abstract>
    <identifier type="citekey">sun-etal-2026-forced</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.30/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>427</start>
            <end>433</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Forced Answer Channel for Closed-Book Knowledge Base Construction at LM-KBC 2026
%A Sun, Yiqun
%A Wei, Pengfei
%A Hsieh, Lawrence B.
%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 sun-etal-2026-forced
%X The AKBC 2026 shared task (Kalo et al., 2026) asks a system to complete the object set of a subject and a relation out of a language model’s parameters, with no retrieval, no training, and no more than 32B parameters. Our system drives one 29.6B backbone through three stages. Several elicitation channels per relation build a candidate pool, exhaustive one-token Yes/No probes verify whatever part of the answer space can be enumerated, and a per-relation decision layer emits the object set. The backbone writes a reasoning channel before its user-facing answer, so a probe prompt has to append the answer-channel header before its first generated token is a verdict. Forcing that channel also makes auxiliary generations cheap, which is what puts roughly 26k border probes inside the budget. Most decision constants are fitted on validation gold under a rule that displaces an incumbent only on a strict improvement of more than one row, and the fitting procedure itself is cross-validated, which cut one city gain from +0.070 to +0.020 before it was adopted. The system scores 0.6553 official macro-F1 against 0.6415 for a prompting baseline on the same backbone, and the gap is uneven: the machinery is worth +0.1662 on awards and costs 0.0204 on hasCapacity, where plain prompting wins. We also report the ceiling we could not move. Twenty-one method families have been fitted against hasCapacity and none of them beats a mass vote over the pool. Harvesting the model’s own reasoning traces raises pool coverage from 0.582 to 0.724 and converts none of it.
%U https://aclanthology.org/2026.akbc-1.30/
%P 427-433

Markdown (Informal)

[A Forced Answer Channel for Closed-Book Knowledge Base Construction at LM-KBC 2026](https://aclanthology.org/2026.akbc-1.30/) (Sun et al., AKBC 2026)

• A Forced Answer Channel for Closed-Book Knowledge Base Construction at LM-KBC 2026 (Sun et al., AKBC 2026)

ACL

• Yiqun Sun, Pengfei Wei, and Lawrence B. Hsieh. 2026. A Forced Answer Channel for Closed-Book Knowledge Base Construction at LM-KBC 2026. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 427–433, Budapest, Hungary. Association for Computational Linguistics.