Litcius/Paper detail

A Trustworthy View on Explainable Artificial Intelligence Method Evaluation

Li Ding, Yan Liu, Jun Huang, Zerui Wang

2023Computer16 citationsDOI

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