Enregistré dans:
Détails bibliographiques
Auteurs principaux: Estienne, Lautaro, Ernst, Erik, Vera, Matías, Piantanida, Pablo, Ferrer, Luciana
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.20490
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914593438171136
author Estienne, Lautaro
Ernst, Erik
Vera, Matías
Piantanida, Pablo
Ferrer, Luciana
author_facet Estienne, Lautaro
Ernst, Erik
Vera, Matías
Piantanida, Pablo
Ferrer, Luciana
contents In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept or reject predictions based on application-specific cost trade-offs. Such uncertainty-augmented (UA) systems -- i.e., systems that output both predictions and uncertainty scores -- are currently being assessed in the literature in a variety of ways, using separate metrics to evaluate the predictions and the uncertainty scores, setting a cost function with a fixed rejection cost or integrating over a coverage-risk curve. We argue that these evaluation approaches are inadequate for assessing overall performance of the UA system for decision making under uncertainty and propose a novel family of metrics, ECUAS$_n$, formulated as proper scoring rules for the task of interest. The parameter $n$ controls the trade-off between the cost of incorrect predictions and imperfect uncertainties depending on the needs of the use-case. We demonstrate the advantages of the ECUAS$_n$ metrics both theoretically and empirically, through experiments on diverse classification and generation datasets, including a manually annotated subset of TriviaQA.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20490
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
Estienne, Lautaro
Ernst, Erik
Vera, Matías
Piantanida, Pablo
Ferrer, Luciana
Artificial Intelligence
Machine Learning
In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept or reject predictions based on application-specific cost trade-offs. Such uncertainty-augmented (UA) systems -- i.e., systems that output both predictions and uncertainty scores -- are currently being assessed in the literature in a variety of ways, using separate metrics to evaluate the predictions and the uncertainty scores, setting a cost function with a fixed rejection cost or integrating over a coverage-risk curve. We argue that these evaluation approaches are inadequate for assessing overall performance of the UA system for decision making under uncertainty and propose a novel family of metrics, ECUAS$_n$, formulated as proper scoring rules for the task of interest. The parameter $n$ controls the trade-off between the cost of incorrect predictions and imperfect uncertainties depending on the needs of the use-case. We demonstrate the advantages of the ECUAS$_n$ metrics both theoretically and empirically, through experiments on diverse classification and generation datasets, including a manually annotated subset of TriviaQA.
title ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.20490