@inproceedings{skorski-2026-moral,
title = "Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment",
author = "Skorski, Maciej",
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.43/",
pages = "704--714",
ISBN = "979-8-89176-486-6",
abstract = "Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into *majority* vote or the more permissive *any-annotator* rule which assigns a label as soon as any annotator flags it.\par We argue this uncertainty should instead be modeled and learned from.\par We introduce **Moral Entropy**, a Bayesian framework that estimates a full posterior over the true label and decomposes its entropy into *aleatoric* uncertainty (irreducible disagreement about the moral content) and *epistemic* uncertainty (from insufficient or noisy annotation). This lets any heuristic consensus rule be audited against a calibrated ground truth via entropy methods such as cross-entropy/KL, Brier score, and expected calibration error.\par Running this model on over 100,000 posts from three corpora spanning fifteen discourse domains, we audit the standard aggregation rules against the resulting posterior and reveal systematic differences in moral labels. Across MFTC and MFRC, the any-annotator rule yields mean false-positive rates of 10.2{--}19.9{\%} and mean false-negative rates of 38.9{--}54.8{\%} relative to the Bayesian consensus, while majority-vote and two-vote rules miss 63{--}83{\%} of reference-positive labels."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skorski-2026-moral">
<titleInfo>
<title>Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Skorski</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>Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into *majority* vote or the more permissive *any-annotator* rule which assigns a label as soon as any annotator flags it.\par We argue this uncertainty should instead be modeled and learned from.\par We introduce **Moral Entropy**, a Bayesian framework that estimates a full posterior over the true label and decomposes its entropy into *aleatoric* uncertainty (irreducible disagreement about the moral content) and *epistemic* uncertainty (from insufficient or noisy annotation). This lets any heuristic consensus rule be audited against a calibrated ground truth via entropy methods such as cross-entropy/KL, Brier score, and expected calibration error.\par Running this model on over 100,000 posts from three corpora spanning fifteen discourse domains, we audit the standard aggregation rules against the resulting posterior and reveal systematic differences in moral labels. Across MFTC and MFRC, the any-annotator rule yields mean false-positive rates of 10.2–19.9% and mean false-negative rates of 38.9–54.8% relative to the Bayesian consensus, while majority-vote and two-vote rules miss 63–83% of reference-positive labels.</abstract>
<identifier type="citekey">skorski-2026-moral</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.43/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>704</start>
<end>714</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
%A Skorski, Maciej
%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 skorski-2026-moral
%X Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into *majority* vote or the more permissive *any-annotator* rule which assigns a label as soon as any annotator flags it.\par We argue this uncertainty should instead be modeled and learned from.\par We introduce **Moral Entropy**, a Bayesian framework that estimates a full posterior over the true label and decomposes its entropy into *aleatoric* uncertainty (irreducible disagreement about the moral content) and *epistemic* uncertainty (from insufficient or noisy annotation). This lets any heuristic consensus rule be audited against a calibrated ground truth via entropy methods such as cross-entropy/KL, Brier score, and expected calibration error.\par Running this model on over 100,000 posts from three corpora spanning fifteen discourse domains, we audit the standard aggregation rules against the resulting posterior and reveal systematic differences in moral labels. Across MFTC and MFRC, the any-annotator rule yields mean false-positive rates of 10.2–19.9% and mean false-negative rates of 38.9–54.8% relative to the Bayesian consensus, while majority-vote and two-vote rules miss 63–83% of reference-positive labels.
%U https://aclanthology.org/2026.uncertainlp-main.43/
%P 704-714
Markdown (Informal)
[Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment](https://aclanthology.org/2026.uncertainlp-main.43/) (Skorski, UncertaiNLP 2026)
ACL