A Trustworthy View on Explainable Artificial Intelligence Method Evaluation

被引：5
|
作者：
Li, Ding [1 ]
Liu, Yan [1 ]
Huang, Jun [1 ]
Wang, Zerui [1 ]
机构：
[1] Concordia Univ, Dept Elect & Comp Engn, Montreal, PQ H3G 1M8, Canada
来源：
COMPUTER | 2023年 / 56卷 / 04期
关键词：
Measurement; Artificial intelligence;
D O I：
10.1109/MC.2022.3233806
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
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.
引用
收藏
页码：50 / 60
页数：11
相关论文
共 50 条
  • [1] Explainable and Trustworthy Artificial Intelligence
    Alonso-Moral, Jose Maria
    Mencar, Corrado
    Ishibuchi, Hisao
    [J]. IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2022, 17 (01) : 14 - 15
  • [2] Blockchain for explainable and trustworthy artificial intelligence
    Nassar, Mohamed
    Salah, Khaled
    Rehman, Muhammad Habib ur
    Svetinovic, Davor
    [J]. WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2020, 10 (01)
  • [3] An Operational Framework for Guiding Human Evaluation in Explainable and Trustworthy Artificial Intelligence
    Confalonieri, Roberto
    Alonso-Moral, Jose Maria
    [J]. IEEE INTELLIGENT SYSTEMS, 2024, 39 (01) : 18 - 28
  • [4] An Overview for Trustworthy and Explainable Artificial Intelligence in Healthcare
    [J]. Arslanoglu, Kubra (karslanoglu@firat.edu.tr), 1600, Institute of Electrical and Electronics Engineers Inc.
  • [5] A Review of Trustworthy and Explainable Artificial Intelligence (XAI)
    Chamola, Vinay
    Hassija, Vikas
    Sulthana, A. Razia
    Ghosh, Debshishu
    Dhingra, Divyansh
    Sikdar, Biplab
    [J]. IEEE ACCESS, 2023, 11 : 78994 - 79015
  • [6] An Explainable Artificial Intelligence Approach for a Trustworthy Spam Detection
    Ibrahim, Abubakr
    Mejri, Mohamed
    Jaafar, Fehmi
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON CYBER SECURITY AND RESILIENCE, CSR, 2023, : 160 - 167
  • [7] Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences
    Feng, Jinchao
    Lansford, Joshua L.
    Katsoulakis, Markos A.
    Vlachos, Dionisios G.
    [J]. SCIENCE ADVANCES, 2020, 6 (42)
  • [8] Recent Advances in Trustworthy Explainable Artificial Intelligence: Status, Challenges, and Perspectives
    Rawal, Atul
    McCoy, James
    Rawat, Danda B.
    Sadler, Brian M.
    Amant, Robert St.
    [J]. IEEE Transactions on Artificial Intelligence, 2022, 3 (06): : 852 - 866
  • [9] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
    Ali, Sajid
    Abuhmed, Tamer
    El-Sappagh, Shaker
    Muhammad, Khan
    Alonso-Moral, Jose M.
    Confalonieri, Roberto
    Guidotti, Riccardo
    Del Ser, Javier
    Diaz-Rodriguez, Natalia
    Herrera, Francisco
    [J]. INFORMATION FUSION, 2023, 99
  • [10] Fund performance evaluation with explainable artificial intelligence
    Kovvuri, Veera Raghava Reddy
    Fu, Hsuan
    Fan, Xiuyi
    Seisenberger, Monika
    [J]. FINANCE RESEARCH LETTERS, 2023, 58
12345