SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction

Jannic Alexander Cutura

SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

The AKBC 2026 shared task asks a language model to recover complete object sets closed-book. SetProbe anchors each subject, samples several candidate sets, and aggregates them per relation, reaching 0.513 macro F1. Sample count, aggregation rule, and abstention thresholds each move the score by less than the evaluation set’s own 0.045 confidence interval; only the choice of model does. The binding constraint is elementary: closed-book prediction cannot recover an object that appears in no sample.

Anthology ID:: 2026.akbc-1.32
Volume:: Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Jan-Christoph Kalo, Ndapa Nakashole, Simon Razniewski, Fabian M. Suchanek, Andreas Vlachos, Andrew McCallum
Venues:: AKBC | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 441–446
Language:
URL:: https://aclanthology.org/2026.akbc-1.32/
DOI:
Bibkey:
Cite (ACL):: Jannic Alexander Cutura. 2026. SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 441–446, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction (Cutura, AKBC 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.akbc-1.32.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{cutura-2026-setprobe,
    title = "{S}et{P}robe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction",
    author = "Cutura, Jannic Alexander",
    editor = "Kalo, Jan-Christoph  and
      Nakashole, Ndapa  and
      Razniewski, Simon  and
      Suchanek, Fabian M.  and
      Vlachos, Andreas  and
      McCallum, Andrew",
    booktitle = "Proceedings of the 11th Workshop on Automated Knowledge Base Construction ({AKBC} 2026)",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.akbc-1.32/",
    pages = "441--446",
    ISBN = "979-8-89176-464-4",
    abstract = "The AKBC 2026 shared task asks a language model to recover complete object sets closed-book. SetProbe anchors each subject, samples several candidate sets, and aggregates them per relation, reaching 0.513 macro F1. Sample count, aggregation rule, and abstention thresholds each move the score by less than the evaluation set{'}s own 0.045 confidence interval; only the choice of model does. The binding constraint is elementary: closed-book prediction cannot recover an object that appears in no sample."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cutura-2026-setprobe">
    <titleInfo>
        <title>SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jannic</namePart>
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Cutura</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 asks a language model to recover complete object sets closed-book. SetProbe anchors each subject, samples several candidate sets, and aggregates them per relation, reaching 0.513 macro F1. Sample count, aggregation rule, and abstention thresholds each move the score by less than the evaluation set’s own 0.045 confidence interval; only the choice of model does. The binding constraint is elementary: closed-book prediction cannot recover an object that appears in no sample.</abstract>
    <identifier type="citekey">cutura-2026-setprobe</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.32/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>441</start>
            <end>446</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction
%A Cutura, Jannic Alexander
%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 cutura-2026-setprobe
%X The AKBC 2026 shared task asks a language model to recover complete object sets closed-book. SetProbe anchors each subject, samples several candidate sets, and aggregates them per relation, reaching 0.513 macro F1. Sample count, aggregation rule, and abstention thresholds each move the score by less than the evaluation set’s own 0.045 confidence interval; only the choice of model does. The binding constraint is elementary: closed-book prediction cannot recover an object that appears in no sample.
%U https://aclanthology.org/2026.akbc-1.32/
%P 441-446

Download as File

Markdown (Informal)

[SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction](https://aclanthology.org/2026.akbc-1.32/) (Cutura, AKBC 2026)

SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction (Cutura, AKBC 2026)

ACL

Jannic Alexander Cutura. 2026. SetProbe: Description-First Relation-Wise Self-Consistency for Closed-Book Knowledge Base Construction. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 441–446, Budapest, Hungary. Association for Computational Linguistics.