Abstract
Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a loan with a shorter term, it would have been approved). Counterfactuals explain what changes to the input-features of an AI system change the output-decision. However, there is a sub-type of counterfactual, semi-factuals, that have received less attention in AI (though the Cognitive Sciences have studied them extensively). This paper surveys these literatures to summarise historical and recent breakthroughs in this area. It defines key desiderata for semi-factual XAI and reports benchmark tests of historical algorithms (along with a novel, naieve method) to provide a solid basis for future algorithmic developments.
Abstract (translated)
最近,eXplainable AI (XAI) research 的重点是针对 AI 系统决策后的解释性解释(例如,一个客户拒绝贷款可能会被告诉:如果要求一个更短的贷款期限,它就会被批准)作为 post-hoc justifys(即事后合理解释)。反事实解释解释了 AI 系统输入特征的变化如何影响输出决策。然而,反事实有一个子类型,即半事实解释,在 AI 中较少受到关注(尽管认知科学已经深入研究了它们)。本文对这些文献进行综述,以总结这一领域的历史和最近的突破。它定义了半事实 XAI 的关键要求,并报告了历史算法的基准测试(同时采用一种新颖、天真的方法),为未来的算法发展提供了坚实的基础。
URL
https://arxiv.org/abs/2301.11970