KAA

Explainability and interpretability are often confused, but explainability concerns the transparency of the system, while interpretability pertains to the human capacity to give meaning to explanations. Comprehensibility and understanding emphasize the importance of human mediation and criticism of explanations, especially in high-risk areas. The European AI Act (2024-2025) and recent work in XAI insist on the need for a situated explainability, adapted to the context and to the user, for a responsible and trustworthy AI.

KAA must be considered as a comprehensibility tool. It is part of these mediation tools allowing to implement explainability methods in a guided way, to facilitate the adjustment of their parameters. It then offers appropriate and relevant interfaces and visualizations of results to select the methods and metrics that are most suited to the user's problem.

It shall be used by ML scientist and engineer during the activity "Develop and acquire ML models" . It should be used for model validation and qualification.