A Trustworthy View on Explainable Artificial Intelligence Method Evaluation

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.

Saved in:
Bibliographic Details
Published inComputer (Long Beach, Calif.) Vol. 56; no. 4; pp. 50 - 60
Main Authors Li, Ding, Liu, Yan, Huang, Jun, Wang, Zerui
Format Journal Article
LanguageEnglish
Published New York IEEE 01.04.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial intelligence
Explainable artificial intelligence
Measurement
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:0018-9162
1558-0814
DOI:10.1109/MC.2022.3233806