What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods.
Julien Colin, Thomas Fel, Rémi Cadène, T. Serre
Abstract
= 1,150) to evaluate the usefulness of representative attribution methods in three real-world scenarios. Our results demonstrate that the degree to which individual attribution methods help human participants better understand an AI system varies widely across these scenarios. This suggests the need to move beyond quantitative improvements of current attribution methods, towards the development of complementary approaches that provide qualitatively different sources of information to human end-users.
Topics & Concepts
AttributionComputer scienceMultitudeData scienceScale (ratio)Human–computer interactionArtificial intelligencePsychologySocial psychologyPhilosophyQuantum mechanicsPhysicsEpistemologyExplainable Artificial Intelligence (XAI)Ethics and Social Impacts of AIDecision-Making and Behavioral Economics