评估静态和变化数据解释方法的挑战

本文解决了可解释人工智能 (XAI) 在评估不足方面的局限性。它们通过用于偏差检测和概念遗忘的 DetoxAI 图像识别系统进行说明。然后,给出了用于解释图像分类的方法的以人为基础的评估示例。本文进一步探讨了使解释适应具有概念漂移的不断演变的数据流的方法。讨论了针对该问题采用反事实的经验。最后，它与跟踪数据,模型,和解释的共同进化的挑战有关。\footnote{本文已被接受在此http URL(ed)可解释的人工智能空间中发表。 IJCAI-ECAI 2026 Bremen EASi 2026 研讨会论文集, Springer CCIS vol 3107 (2016).}

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 this http URL (ed) Explainable AI in Space. Proceedings of EASi 2026 Workshop at IJCAI-ECAI 2026 Bremen, Springer CCIS vol 3107 (2016).}

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)