Directive Explanations for Actionable Explainability in Machine Learning Applications
Directive Explanations for Actionable Explainability in Machine Learning Applications
复制标题
DOI：
10.1145/3579363
复制
发表时间：
2021-02
影响因子：
3.4
通讯作者：
Ronal Singh;Paul Dourish;P. Howe;Tim Miller;L. Sonenberg;Eduardo Velloso;F. Vetere
中科院分区：
文献类型：
--
作者：
Ronal Singh;Paul Dourish;P. Howe;Tim Miller;L. Sonenberg;Eduardo Velloso;F. Vetere
在本文中，我们表明，不仅可以解释为什么做出决策，还可以解释个人如何获得期望的结果，从而可以改进机器学习系统做出的决策的解释。我们正式定义指令解释的概念（提供个人可以采取的具体行动以实现其期望结果的指令解释），引入两种形式的指令解释（特定指令和通用指令），并描述如何通过计算生成这些指令。我们通过两项在线研究调查人们对指导性解释的偏好和看法，一项是定量的，另一项是定性的，每个研究涵盖两个领域（信用评分领域和员工满意度领域）。我们发现与非指令性反事实解释相比，人们对两种形式的指令性解释都有显着的偏好。然而，我们也发现偏好受到很多方面的影响，包括个人偏好和社会因素。我们的结论是，决定提供什么类型的解释需要有关接收者的信息和其他上下文信息。这强化了对以人为中心且针对具体情况的方法来解释可解释的人工智能的需求。
In this article, we show that explanations of decisions made by machine learning systems can be improved by not only explaining why a decision was made but also explaining how an individual could obtain their desired outcome. We formally define the concept of directive explanations (those that offer specific actions an individual could take to achieve their desired outcome), introduce two forms of directive explanations (directive-specific and directive-generic), and describe how these can be generated computationally. We investigate people’s preference for and perception toward directive explanations through two online studies, one quantitative and the other qualitative, each covering two domains (the credit scoring domain and the employee satisfaction domain). We find a significant preference for both forms of directive explanations compared to non-directive counterfactual explanations. However, we also find that preferences are affected by many aspects, including individual preferences and social factors. We conclude that deciding what type of explanation to provide requires information about the recipients and other contextual information. This reinforces the need for a human-centered and context-specific approach to explainable AI.