A Trustworthy View on Explainable Artificial Intelligence Method Evaluation
Li Ding, Yan Liu, Jun Huang, Zerui Wang
Abstract
In this article, we follow a process of explainable artificial intelligence (XAI) method development and define two metrics in terms of consistency and efficiency in guiding the evaluation of XAI explanations.
Topics & Concepts
TrustworthinessConsistency (knowledge bases)Computer scienceProcess (computing)Artificial intelligenceComputer securityOperating systemExplainable Artificial Intelligence (XAI)Adversarial Robustness in Machine LearningArtificial Intelligence in Healthcare and Education