@inproceedings{andrade-etal-2026-beyond,
title = "Beyond Global Calibration: Analyzing Class-Specific Miscalibration and High-Confidence Errors in Text Classification",
author = "Andrade, Claudio Mois{\'e}s Valiense de and
Fonseca, Guilherme and
Cunha, Washington and
Fran{\c{c}}a, Celso and
Pagano, Adriana Silvina and
Rocha, Leonardo Chaves Dutra da and
Andr{\'e} Gon{\c{c}}alves, Marcos",
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.41/",
pages = "683--692",
ISBN = "979-8-89176-486-6",
abstract = "Confidence scores are increasingly used to assess uncertainty in text classification, yet aggregate calibration metrics may hide localized reliability failures. We investigate this issue across seven sentiment and topic classification datasets by comparing global and class-specific calibration and analyzing high-confidence errors. Our results show that low global calibration error can coexist with substantial class-specific variation, particularly in multi-class settings. We also find that high-confidence errors are not randomly distributed: they concentrate in specific true{--}predicted class confusions, with some incorrect predictions receiving confidence scores close to 1.0. These findings show that globally calibrated models can still exhibit systematic uncertainty failures, motivating class-aware and error-level analyses when confidence is used as an indicator of prediction reliability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andrade-etal-2026-beyond">
<titleInfo>
<title>Beyond Global Calibration: Analyzing Class-Specific Miscalibration and High-Confidence Errors in Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="given">Moisés</namePart>
<namePart type="given">Valiense</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Andrade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="family">Fonseca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Washington</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celso</namePart>
<namePart type="family">França</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriana</namePart>
<namePart type="given">Silvina</namePart>
<namePart type="family">Pagano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="given">Chaves</namePart>
<namePart type="given">Dutra</namePart>
<namePart type="given">da</namePart>
<namePart type="family">Rocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">André Gonçalves</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>Confidence scores are increasingly used to assess uncertainty in text classification, yet aggregate calibration metrics may hide localized reliability failures. We investigate this issue across seven sentiment and topic classification datasets by comparing global and class-specific calibration and analyzing high-confidence errors. Our results show that low global calibration error can coexist with substantial class-specific variation, particularly in multi-class settings. We also find that high-confidence errors are not randomly distributed: they concentrate in specific true–predicted class confusions, with some incorrect predictions receiving confidence scores close to 1.0. These findings show that globally calibrated models can still exhibit systematic uncertainty failures, motivating class-aware and error-level analyses when confidence is used as an indicator of prediction reliability.</abstract>
<identifier type="citekey">andrade-etal-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.41/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>683</start>
<end>692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Global Calibration: Analyzing Class-Specific Miscalibration and High-Confidence Errors in Text Classification
%A Andrade, Claudio Moisés Valiense de
%A Fonseca, Guilherme
%A Cunha, Washington
%A França, Celso
%A Pagano, Adriana Silvina
%A Rocha, Leonardo Chaves Dutra da
%A André Gonçalves, Marcos
%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 andrade-etal-2026-beyond
%X Confidence scores are increasingly used to assess uncertainty in text classification, yet aggregate calibration metrics may hide localized reliability failures. We investigate this issue across seven sentiment and topic classification datasets by comparing global and class-specific calibration and analyzing high-confidence errors. Our results show that low global calibration error can coexist with substantial class-specific variation, particularly in multi-class settings. We also find that high-confidence errors are not randomly distributed: they concentrate in specific true–predicted class confusions, with some incorrect predictions receiving confidence scores close to 1.0. These findings show that globally calibrated models can still exhibit systematic uncertainty failures, motivating class-aware and error-level analyses when confidence is used as an indicator of prediction reliability.
%U https://aclanthology.org/2026.uncertainlp-main.41/
%P 683-692
Markdown (Informal)
[Beyond Global Calibration: Analyzing Class-Specific Miscalibration and High-Confidence Errors in Text Classification](https://aclanthology.org/2026.uncertainlp-main.41/) (Andrade et al., UncertaiNLP 2026)
ACL