Data Representing Ground-Truth Explanations to Evaluate XAI Methods

no code implementations • 18 Nov 2020 • Shideh Shams Amiri, Rosina O. Weber, Prateek Goel, Owen Brooks, Archer Gandley, Brian Kitchell, Aaron Zehm

The contributions of this paper include a methodology to create synthetic data representing ground-truth explanations, three data sets, an evaluation of LIME using these data sets, and a preliminary analysis of the challenges and potential benefits in using these data to evaluate existing XAI approaches.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1