@inproceedings{wedda-valdenegro-toro-2026-overlap,
title = "Overlap-Based {OOD} Detection in Closed-Book Question Answering",
author = "Wedda, Dries and
Valdenegro-Toro, Matias",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.30/",
pages = "481--494",
ISBN = "979-8-89176-486-6",
abstract = "Closed-book question answering requires models to answer using knowledge stored in their parameters, making uncertainty estimation important when that knowledge is limited. We study how total, aleatoric, and epistemic uncertainty respond to progressively weaker train-test overlap, from question paraphrase overlap to answer-only overlap to no overlap, and how well these estimates detect overlap-based out-of-distribution questions. Using T5-Large-SSM on WebQuestions and Open Natural Questions, we estimate token-level uncertainty with Deep Ensembles and Monte Carlo Dropout and sequence-level uncertainty with Deep Ensembles. Weaker overlap is associated with higher total and epistemic uncertainty, but aleatoric uncertainty also tends to increase. Epistemic uncertainty performs best for OOD detection on Open Natural Questions, but does not consistently outperform total or aleatoric uncertainty on WebQuestions. These findings show that train-test overlap is reflected in uncertainty estimates, but the response to weaker overlap is not consistently isolated to the epistemic component."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wedda-valdenegro-toro-2026-overlap">
<titleInfo>
<title>Overlap-Based OOD Detection in Closed-Book Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dries</namePart>
<namePart type="family">Wedda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matias</namePart>
<namePart type="family">Valdenegro-Toro</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>Closed-book question answering requires models to answer using knowledge stored in their parameters, making uncertainty estimation important when that knowledge is limited. We study how total, aleatoric, and epistemic uncertainty respond to progressively weaker train-test overlap, from question paraphrase overlap to answer-only overlap to no overlap, and how well these estimates detect overlap-based out-of-distribution questions. Using T5-Large-SSM on WebQuestions and Open Natural Questions, we estimate token-level uncertainty with Deep Ensembles and Monte Carlo Dropout and sequence-level uncertainty with Deep Ensembles. Weaker overlap is associated with higher total and epistemic uncertainty, but aleatoric uncertainty also tends to increase. Epistemic uncertainty performs best for OOD detection on Open Natural Questions, but does not consistently outperform total or aleatoric uncertainty on WebQuestions. These findings show that train-test overlap is reflected in uncertainty estimates, but the response to weaker overlap is not consistently isolated to the epistemic component.</abstract>
<identifier type="citekey">wedda-valdenegro-toro-2026-overlap</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>481</start>
<end>494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overlap-Based OOD Detection in Closed-Book Question Answering
%A Wedda, Dries
%A Valdenegro-Toro, Matias
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F wedda-valdenegro-toro-2026-overlap
%X Closed-book question answering requires models to answer using knowledge stored in their parameters, making uncertainty estimation important when that knowledge is limited. We study how total, aleatoric, and epistemic uncertainty respond to progressively weaker train-test overlap, from question paraphrase overlap to answer-only overlap to no overlap, and how well these estimates detect overlap-based out-of-distribution questions. Using T5-Large-SSM on WebQuestions and Open Natural Questions, we estimate token-level uncertainty with Deep Ensembles and Monte Carlo Dropout and sequence-level uncertainty with Deep Ensembles. Weaker overlap is associated with higher total and epistemic uncertainty, but aleatoric uncertainty also tends to increase. Epistemic uncertainty performs best for OOD detection on Open Natural Questions, but does not consistently outperform total or aleatoric uncertainty on WebQuestions. These findings show that train-test overlap is reflected in uncertainty estimates, but the response to weaker overlap is not consistently isolated to the epistemic component.
%U https://aclanthology.org/2026.uncertainlp-main.30/
%P 481-494
Markdown (Informal)
[Overlap-Based OOD Detection in Closed-Book Question Answering](https://aclanthology.org/2026.uncertainlp-main.30/) (Wedda & Valdenegro-Toro, UncertaiNLP 2026)
ACL