The Quest for Reliable Metrics of Responsible AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rampisela, Theresia Veronika, Maistro, Maria, Ruotsalo, Tuukka, Lioma, Christina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912678099812352
author Rampisela, Theresia Veronika
Maistro, Maria
Ruotsalo, Tuukka
Lioma, Christina
author_facet Rampisela, Theresia Veronika
Maistro, Maria
Ruotsalo, Tuukka
Lioma, Christina
contents The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quantified through evaluation metrics, yet there has been less work on assessing the robustness and reliability of the metrics themselves. We reflect on prior work that examines the robustness of fairness metrics for recommender systems as a type of AI application and summarise their key takeaways into a set of non-exhaustive guidelines for developing reliable metrics of responsible AI. Our guidelines apply to a broad spectrum of AI applications, including AIS.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Quest for Reliable Metrics of Responsible AI
Rampisela, Theresia Veronika
Maistro, Maria
Ruotsalo, Tuukka
Lioma, Christina
Computers and Society
Artificial Intelligence
Information Retrieval
Machine Learning
The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quantified through evaluation metrics, yet there has been less work on assessing the robustness and reliability of the metrics themselves. We reflect on prior work that examines the robustness of fairness metrics for recommender systems as a type of AI application and summarise their key takeaways into a set of non-exhaustive guidelines for developing reliable metrics of responsible AI. Our guidelines apply to a broad spectrum of AI applications, including AIS.
title The Quest for Reliable Metrics of Responsible AI
topic Computers and Society
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2510.26007