@inproceedings{zimmermann-2026-muselist,
title = "{M}use{L}ist: Confidence-Gated Multi-Surface Recall for Closed-Book Knowledge Base Construction",
author = "Zimmermann, Adrian",
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-1.39/",
pages = "496--517",
ISBN = "979-8-89176-464-4",
abstract = "Knowledge base construction requires complete answer sets, not just one plausible fact. We present MuseList, a closed-book system for the six-relation AKBC Shared Task 2026. A single open-weight 29.8B-parameter Muse Glimmer model generates candidate answers in several formats, such as recipient lists, recipient{--}year tables, and venue records. All such records are model-generated; the system retrieves no external documents. Relation-specific rules combine these candidates, select numerical answers using token-level confidence signals, and check proposed reciprocal borders with three separately prompted roles. The complete system scores 0.6700 hidden-test macro-F1 and ranks fourth among twelve systems. Its development validation score is 0.69160; this split informed method selection and is not an untouched evaluation. We describe the method and release an archive that reconstructs the scored submission exactly. Fresh-call support is separate and partial: it regenerates later-stage responses, not an end-to-end submission."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zimmermann-2026-muselist">
<titleInfo>
<title>MuseList: Confidence-Gated Multi-Surface Recall for Closed-Book Knowledge Base Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Zimmermann</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>Knowledge base construction requires complete answer sets, not just one plausible fact. We present MuseList, a closed-book system for the six-relation AKBC Shared Task 2026. A single open-weight 29.8B-parameter Muse Glimmer model generates candidate answers in several formats, such as recipient lists, recipient–year tables, and venue records. All such records are model-generated; the system retrieves no external documents. Relation-specific rules combine these candidates, select numerical answers using token-level confidence signals, and check proposed reciprocal borders with three separately prompted roles. The complete system scores 0.6700 hidden-test macro-F1 and ranks fourth among twelve systems. Its development validation score is 0.69160; this split informed method selection and is not an untouched evaluation. We describe the method and release an archive that reconstructs the scored submission exactly. Fresh-call support is separate and partial: it regenerates later-stage responses, not an end-to-end submission.</abstract>
<identifier type="citekey">zimmermann-2026-muselist</identifier>
<location>
<url>https://aclanthology.org/2026.akbc-1.39/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>496</start>
<end>517</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuseList: Confidence-Gated Multi-Surface Recall for Closed-Book Knowledge Base Construction
%A Zimmermann, Adrian
%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 zimmermann-2026-muselist
%X Knowledge base construction requires complete answer sets, not just one plausible fact. We present MuseList, a closed-book system for the six-relation AKBC Shared Task 2026. A single open-weight 29.8B-parameter Muse Glimmer model generates candidate answers in several formats, such as recipient lists, recipient–year tables, and venue records. All such records are model-generated; the system retrieves no external documents. Relation-specific rules combine these candidates, select numerical answers using token-level confidence signals, and check proposed reciprocal borders with three separately prompted roles. The complete system scores 0.6700 hidden-test macro-F1 and ranks fourth among twelve systems. Its development validation score is 0.69160; this split informed method selection and is not an untouched evaluation. We describe the method and release an archive that reconstructs the scored submission exactly. Fresh-call support is separate and partial: it regenerates later-stage responses, not an end-to-end submission.
%U https://aclanthology.org/2026.akbc-1.39/
%P 496-517
Markdown (Informal)
[MuseList: Confidence-Gated Multi-Surface Recall for Closed-Book Knowledge Base Construction](https://aclanthology.org/2026.akbc-1.39/) (Zimmermann, AKBC 2026)
ACL