SIDEs：分离xAI中理想化与欺骗性解释

可解释AI（xAI）方法对于建立使用黑箱模型的信任至关重要。然而，近期对当前xAI方法的批评日益增长，指控其结果不一致、必然为假且可能被操纵，这些批评开始动摇黑箱模型的部署。鲁丁（2019）甚至认为，我们应该停止在高风险案例中使用黑箱模型，因为xAI解释“必须是错误的”。然而，严格忠于真实的是科学历史上并非理想目标的。理想化——在科学理论和模型中刻意引入的扭曲——在自然科学中十分常见，被视为成功的科学工具。因此，问题不在于错误本身。在本文中，我概述了xAI研究需要从事理想化评估的需求。drawing on the use of idealizations in the natural sciences and philosophy of science, I introduce a novel framework for evaluating whether xAI methods engage in successful idealizations or deceptive explanations (SIDEs). SIDEs evaluates whether the limitations of xAI methods, and the distortions that they introduce, can be part of a successful idealization or are indeed deceptive distortions as critics suggest. I discuss the role that existing research can play in idealization evaluation and where innovation is necessary. Through a qualitative analysis we find that leading feature importance methods and counterfactual explanations are subject to idealization failure and suggest remedies for ameliorating idealization failure.