Challenges in Evaluating Explanation Methods for Static and Evolving Data· 静态和动态数据解释方法的挑战
This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept unlearning. Then, an example of a human-grounded evaluation of methods for explaining image classification is presented. The paper further explores methods for adapting explanations to evolving data streams with concept drift. Experiences with adapting counterfactuals for this problem are discussed. Finally it is related to the challenges of tracking the co-evolution of data, models, and explanations.\footnote{This paper has been accepted for a publication in J.Nalepa (ed) Explainable AI in Space. Proceedings of EASi 2026 Workshop at IJCAI-ECAI 2026 Bremen, Springer CCIS vo
探讨XAI在静态和动态数据解释中的评估挑战及适应方法。
- 核心方法
- 使用DetoxAI系统演示偏见检测和概念遗忘，介绍基于人类评估的图像分类解释方法及适应动态数据流的反事实解释调整。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- XAI方法在静态和动态数据（特别是概念漂移时）的评估不足问题。
- 关键实验
- 通过DetoxAI系统和基于人类评估的图像分类解释方法实验。
- 主要贡献
- 揭示XAI评估不足问题，提出适应动态数据流的解释方法。
- 意义与局限
- 有助于改善XAI方法的评估体系，促进其在动态环境中的应用，但也指出数据、模型和解释共同演化带来的挑战。