@inproceedings{wei-etal-2026-knowledge,
title = "Knowledge Base Construction from Language Models: Mechanisms and Calibrations for Multi-Object Relational Extraction under Parameter Budgets",
author = "Wei, Chengcheng and
Chen, Ze and
Zheng, Jiewen and
He, Jiarong and
Gao, Max",
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-1.34/",
pages = "456--461",
ISBN = "979-8-89176-464-4",
abstract = "We describe our system for the AKBC Shared Task 2026, which asks participants to build knowledge base entries from open-weight language models under a strict 32B total-parameter budget, closed-book setting, and no fine-tuning. Our system combines three complementary families of techniques: (i){~}\textit{diversity-based generation}, which uses multi-question paraphrase prompting and temperature sampling with self-consistency voting to maximize recall; (ii){~}\textit{gold-caliber post-processing}, a set of generic rules that align model outputs to the gold annotation caliber (e.g., collapsing regional stock exchanges, filtering contested territories, and calibrating capacity estimates by rounding patterns); and (iii){~}\textit{confidence-based gating}, which uses log-probability signals to reject low-confidence answers and to verify candidates through independent knowledge pathways. On the validation set our best single-model configuration (Mistral-24B, 24B parameters) reaches a macro-F1 of 0.6562. We additionally analyze which strategies transfer across base models and which fail, providing a practical recipe for closed-book KB construction within tight parameter budgets.[Code is available at {\ensuremath{<}}https://github.com/LexieeWei/akbc2026{\ensuremath{>}}.]"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-knowledge">
<titleInfo>
<title>Knowledge Base Construction from Language Models: Mechanisms and Calibrations for Multi-Object Relational Extraction under Parameter Budgets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengcheng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ze</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiewen</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Gao</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 system for the AKBC Shared Task 2026, which asks participants to build knowledge base entries from open-weight language models under a strict 32B total-parameter budget, closed-book setting, and no fine-tuning. Our system combines three complementary families of techniques: (i) diversity-based generation, which uses multi-question paraphrase prompting and temperature sampling with self-consistency voting to maximize recall; (ii) gold-caliber post-processing, a set of generic rules that align model outputs to the gold annotation caliber (e.g., collapsing regional stock exchanges, filtering contested territories, and calibrating capacity estimates by rounding patterns); and (iii) confidence-based gating, which uses log-probability signals to reject low-confidence answers and to verify candidates through independent knowledge pathways. On the validation set our best single-model configuration (Mistral-24B, 24B parameters) reaches a macro-F1 of 0.6562. We additionally analyze which strategies transfer across base models and which fail, providing a practical recipe for closed-book KB construction within tight parameter budgets.[Code is available at \ensuremath<https://github.com/LexieeWei/akbc2026\ensuremath>.]</abstract>
<identifier type="citekey">wei-etal-2026-knowledge</identifier>
<location>
<url>https://aclanthology.org/2026.akbc-1.34/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>456</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Base Construction from Language Models: Mechanisms and Calibrations for Multi-Object Relational Extraction under Parameter Budgets
%A Wei, Chengcheng
%A Chen, Ze
%A Zheng, Jiewen
%A He, Jiarong
%A Gao, Max
%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 wei-etal-2026-knowledge
%X We describe our system for the AKBC Shared Task 2026, which asks participants to build knowledge base entries from open-weight language models under a strict 32B total-parameter budget, closed-book setting, and no fine-tuning. Our system combines three complementary families of techniques: (i) diversity-based generation, which uses multi-question paraphrase prompting and temperature sampling with self-consistency voting to maximize recall; (ii) gold-caliber post-processing, a set of generic rules that align model outputs to the gold annotation caliber (e.g., collapsing regional stock exchanges, filtering contested territories, and calibrating capacity estimates by rounding patterns); and (iii) confidence-based gating, which uses log-probability signals to reject low-confidence answers and to verify candidates through independent knowledge pathways. On the validation set our best single-model configuration (Mistral-24B, 24B parameters) reaches a macro-F1 of 0.6562. We additionally analyze which strategies transfer across base models and which fail, providing a practical recipe for closed-book KB construction within tight parameter budgets.[Code is available at \ensuremath<https://github.com/LexieeWei/akbc2026\ensuremath>.]
%U https://aclanthology.org/2026.akbc-1.34/
%P 456-461
Markdown (Informal)
[Knowledge Base Construction from Language Models: Mechanisms and Calibrations for Multi-Object Relational Extraction under Parameter Budgets](https://aclanthology.org/2026.akbc-1.34/) (Wei et al., AKBC 2026)
ACL