Scholarlink

<p>This paper addresses methods for evaluating Explainable Artificial Intelligence as a Service (XAIaaS). Existing approaches to evaluating explainable artificial intelligence systems are analyzed. The study aims to develop a method and an evaluation procedure for determining the quality of explainable artificial intelligence systems within the XAIaaS model based on a characteristic-oriented methodology. A multilevel evaluation scheme is proposed, which involves step-by-step analysis, testing, and refinement relying on the key characteristics defined at the first level of the quality model hierarchy. The scheme enables performing a targeted, structured, and comparative assessment of individual properties of the system as a whole. The applicability of the proposed methodology is demonstrated using a practical example.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Explainable Artificial Intelligence as a Service: Algorithms for Evaluation of Characteristics

  • 期刊论文

  • 发表日期：

    2026年1月1日

查看全文
  • V. Kharchenko,
  • S. Yakovlev,
  • O. Veprytska,
  • H. Fesenko

摘要

This paper addresses methods for evaluating Explainable Artificial Intelligence as a Service (XAIaaS). Existing approaches to evaluating explainable artificial intelligence systems are analyzed. The study aims to develop a method and an evaluation procedure for determining the quality of explainable artificial intelligence systems within the XAIaaS model based on a characteristic-oriented methodology. A multilevel evaluation scheme is proposed, which involves step-by-step analysis, testing, and refinement relying on the key characteristics defined at the first level of the quality model hierarchy. The scheme enables performing a targeted, structured, and comparative assessment of individual properties of the system as a whole. The applicability of the proposed methodology is demonstrated using a practical example.