用精益和论证性解释来解释决策
Explainable Decision Making with Lean and Argumentative Explanations
摘要：
人们普遍认为，自动化决策的透明度对于智能系统的可部署性至关重要，解释为什么有些决策是“好”的，而有些则不是，是实现这种透明度的一种方法。我们考虑决策的两种变体，其中“好”的决策相当于（i）满足“大多数”目标的替代方案，以及（ii）满足“最优选”目标。然后，我们定义，对于每个变量和概念的“善良”（与文献中的一些现有概念相对应），以两种格式解释，为具有不同需求和能力的受众选择替代方案的理由：精益的解释，在满足的目标方面，对于一些“善良”的概念，替代性的决定，和论证性的解释，反映导致选择的决策过程，同时对应于精益解释。为了定义论证性解释，我们使用基于推理的论证（ABA），一种众所周知的结构化论证形式。具体来说，我们定义ABA框架，使“好”的决定是可受理的ABA参数，并从争议树制裁这种可受理性的争论性解释。最后，我们实例化我们的整体框架，可解释的决策，以适应目标和决策之间的连接，决策图纳入废止和非废止信息。
英文摘要：
It is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some decisions are "good" and some are not is a way to achieving this transparency. We consider two variants of decision making, where "good" decisions amount to alternatives (i) meeting "most" goals, and (ii) meeting "most preferred" goals. We then define, for each variant and notion of "goodness" (corresponding to a number of existing notions in the literature), explanations in two formats, for justifying the selection of an alternative to audiences with differing needs and competences: lean explanations, in terms of goals satisfied and, for some notions of "goodness", alternative decisions, and argumentative explanations, reflecting the decision process leading to the selection, while corresponding to the lean explanations. To define argumentative explanations, we use assumption-based argumentation (ABA), a well-known form of structured argumentation. Specifically, we define ABA frameworks such that "good" decisions are admissible ABA arguments and draw argumentative explanations from dispute trees sanctioning this admissibility. Finally, we instantiate our overall framework for explainable decision-making to accommodate connections between goals and decisions in terms of decision graphs incorporating defeasible and non-defeasible information.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
