@inproceedings{patcharatrakul-vateekul-2026-datamind,
title = "{D}ata{M}ind at {AKBC} Shared Task 2026: Relation-Specific Multiple Prompting for Closed-Book Knowledge Base Completion",
author = "Patcharatrakul, Tanaree and
Vateekul, Peerapon",
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-1.44/",
pages = "550--559",
ISBN = "979-8-89176-464-4",
abstract = "We describe a system for the AKBC Shared Task 2026. The task is to predict complete sets of knowledge base objects from parametric memory alone, with no retrieval and no fine-tuning, across six relations and within a 32B parameter budget. Our system combines relation-specific multiple prompting, consistency-based aggregation, and error-driven prompt refinement. For each relation, multiple prompt variants and samples elicit complementary predictions, with cross-prompt agreement reducing wording-specific errors and cross-sample agreement filtering unstable guesses. Aggregation is tailored to each relation, including cluster-median aggregation for numeric values and voting for categorical and set-valued outputs. The system achieves a validation macro-F1 of 0.5577 and a test macro-F1 of 0.5699, compared to organizer baselines of 0.3131 (validation) and 0.2964 (test)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="patcharatrakul-vateekul-2026-datamind">
<titleInfo>
<title>DataMind at AKBC Shared Task 2026: Relation-Specific Multiple Prompting for Closed-Book Knowledge Base Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanaree</namePart>
<namePart type="family">Patcharatrakul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerapon</namePart>
<namePart type="family">Vateekul</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 a system for the AKBC Shared Task 2026. The task is to predict complete sets of knowledge base objects from parametric memory alone, with no retrieval and no fine-tuning, across six relations and within a 32B parameter budget. Our system combines relation-specific multiple prompting, consistency-based aggregation, and error-driven prompt refinement. For each relation, multiple prompt variants and samples elicit complementary predictions, with cross-prompt agreement reducing wording-specific errors and cross-sample agreement filtering unstable guesses. Aggregation is tailored to each relation, including cluster-median aggregation for numeric values and voting for categorical and set-valued outputs. The system achieves a validation macro-F1 of 0.5577 and a test macro-F1 of 0.5699, compared to organizer baselines of 0.3131 (validation) and 0.2964 (test).</abstract>
<identifier type="citekey">patcharatrakul-vateekul-2026-datamind</identifier>
<location>
<url>https://aclanthology.org/2026.akbc-1.44/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>550</start>
<end>559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DataMind at AKBC Shared Task 2026: Relation-Specific Multiple Prompting for Closed-Book Knowledge Base Completion
%A Patcharatrakul, Tanaree
%A Vateekul, Peerapon
%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 patcharatrakul-vateekul-2026-datamind
%X We describe a system for the AKBC Shared Task 2026. The task is to predict complete sets of knowledge base objects from parametric memory alone, with no retrieval and no fine-tuning, across six relations and within a 32B parameter budget. Our system combines relation-specific multiple prompting, consistency-based aggregation, and error-driven prompt refinement. For each relation, multiple prompt variants and samples elicit complementary predictions, with cross-prompt agreement reducing wording-specific errors and cross-sample agreement filtering unstable guesses. Aggregation is tailored to each relation, including cluster-median aggregation for numeric values and voting for categorical and set-valued outputs. The system achieves a validation macro-F1 of 0.5577 and a test macro-F1 of 0.5699, compared to organizer baselines of 0.3131 (validation) and 0.2964 (test).
%U https://aclanthology.org/2026.akbc-1.44/
%P 550-559
Markdown (Informal)
[DataMind at AKBC Shared Task 2026: Relation-Specific Multiple Prompting for Closed-Book Knowledge Base Completion](https://aclanthology.org/2026.akbc-1.44/) (Patcharatrakul & Vateekul, AKBC 2026)
ACL