3 papers
cs.LG2025
Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness
Ilaria Vascotto, Alex Rodriguez, Alessandro Bonaita +1
The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a te…
cs.LG2025
Assessing reliability of explanations in unbalanced datasets: a use-case on the occurrence of frost events
Ilaria Vascotto, Valentina Blasone, Alex Rodriguez +2
The usage of eXplainable Artificial Intelligence (XAI) methods has become essential in practical applications, given the increasing deployment of Artificial Intelligence (AI) model…
cs.LG2025
When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances
Ilaria Vascotto, Alex Rodriguez, Alessandro Bonaita +1
Recent legislative regulations have underlined the need for accountable and transparent artificial intelligence systems and have contributed to a growing interest in the Explainabl…