<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sasaki-2026-exemplars">
    <titleInfo>
        <title>Exemplars Primarily Shift Retrieval, Verification Instructions Can Shift Rejection: An Anatomy of Inference-Time Interventions for Closed-Book Knowledge Base Construction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Takashi</namePart>
        <namePart type="family">Sasaki</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>We describe our AKBC 2026 closed-book knowledge base construction system: Gemma-3-27B-pt, raw text completion, 20 candidates per query, and relation-specific aggregation without an arbiter. It uses 27.4B parameters and scores 0.6670 row-averaged Macro F1 on the official test, placing sixth. Experiments distinguish this final pipeline from an earlier Mistral system with an 8B arbiter. Backbone and access format outweighed prompt-level interventions: under matched prompt formats, the pretrained checkpoint exceeds its instruction-tuned sibling by 0.11 on validation. Numeric example configurations primarily shift retrieval; procedural wording with five added JSON examples changes the selected answers by only one row. Verification instructions can shift rejection. A biography-first city prompt format affects both, raising validation F1 from 0.55 to 0.61 at a fixed vote gate. Gating, information outside the model, and seed stability help interpret transfer. These findings have counterexamples; leaderboard comparisons describe development outcomes, not an untouched final evaluation.</abstract>
    <identifier type="citekey">sasaki-2026-exemplars</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.36/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>473</start>
            <end>479</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exemplars Primarily Shift Retrieval, Verification Instructions Can Shift Rejection: An Anatomy of Inference-Time Interventions for Closed-Book Knowledge Base Construction
%A Sasaki, Takashi
%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 sasaki-2026-exemplars
%X We describe our AKBC 2026 closed-book knowledge base construction system: Gemma-3-27B-pt, raw text completion, 20 candidates per query, and relation-specific aggregation without an arbiter. It uses 27.4B parameters and scores 0.6670 row-averaged Macro F1 on the official test, placing sixth. Experiments distinguish this final pipeline from an earlier Mistral system with an 8B arbiter. Backbone and access format outweighed prompt-level interventions: under matched prompt formats, the pretrained checkpoint exceeds its instruction-tuned sibling by 0.11 on validation. Numeric example configurations primarily shift retrieval; procedural wording with five added JSON examples changes the selected answers by only one row. Verification instructions can shift rejection. A biography-first city prompt format affects both, raising validation F1 from 0.55 to 0.61 at a fixed vote gate. Gating, information outside the model, and seed stability help interpret transfer. These findings have counterexamples; leaderboard comparisons describe development outcomes, not an untouched final evaluation.
%U https://aclanthology.org/2026.akbc-1.36/
%P 473-479

Markdown (Informal)

[Exemplars Primarily Shift Retrieval, Verification Instructions Can Shift Rejection: An Anatomy of Inference-Time Interventions for Closed-Book Knowledge Base Construction](https://aclanthology.org/2026.akbc-1.36/) (Sasaki, AKBC 2026)

• Exemplars Primarily Shift Retrieval, Verification Instructions Can Shift Rejection: An Anatomy of Inference-Time Interventions for Closed-Book Knowledge Base Construction (Sasaki, AKBC 2026)

ACL

• Takashi Sasaki. 2026. Exemplars Primarily Shift Retrieval, Verification Instructions Can Shift Rejection: An Anatomy of Inference-Time Interventions for Closed-Book Knowledge Base Construction. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 473–479, Budapest, Hungary. Association for Computational Linguistics.