Toward a novel measure of user trust in XAI systems
The increasing reliance on Deep Learning models, combined with their inherent lack of transparency, has spurred the development of a novel field of study known as eXplainable AI (XAI) methods. These methods aim to enhance end-users' trust in automated systems by providing insights into the rationale behind their decisions. This paper presents a novel trust measure in XAI systems, allowing their refinement. Our proposed metric combines both performance metrics and trust indicators from an objective perspective. To validate this novel methodology, we conducted three case studies showing an improvement with respect to the state-of-the-art, with an increased sensitivity to different scenarios.
Authors
- Antoni Jaume-i-Capó (ORCID: https://orcid.org/0000-0003-3312-5347)
- Gabriel Moyà-Alcover (ORCID: https://orcid.org/0000-0002-3412-5499)
- Miquel Miró-Nicolau (ORCID: https://orcid.org/0000-0002-4092-6583)
- Juan Antonio Palmer Sancho
- Maria Gemma Sempere Campello
- Adel Ghazel (ORCID: https://orcid.org/0000-0001-5286-2110)
- Manuel González-Hidalgo
Institutions
- Normandie Université (FR)
- Health Research Institute of the Balearic Islands (ES)
- Hospital Universitario Son Espases (ES)
- Universitat de les Illes Balears (ES)
- Université de Rouen Normandie (FR)
Publication Details
- Journal
- Frontiers in Computer Science
- Published
- 2026-04-28
- DOI
- https://doi.org/10.3389/fcomp.2026.1746591
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Ministerio de Ciencia, Innovación y Universidades