用行为的民间概念诊断AI解释方法
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
AI总结：
研究提出用行为的民间概念作为框架诊断XAI方法，通过解释性叙事蓝图揭示现有方法缺失的信息构造，以降低人类误解AI行为的可能性。
摘要：
我们研究了一种关于AI成功解释条件的形式化方法。我们认为“成功”不仅取决于解释包含什么信息，还取决于人类解释接收者从中理解了什么信息。心智理论文献讨论了人类用来理解和泛化行为的民间概念。我们假设行为的民间概念为人类提供了一种理解行为的“语言”。我们通过引入一个解释性叙事蓝图（图1），将这些民间概念作为人类解释接收者进行社会归因的框架——即人类可能从解释中理解的信息构造——来用这些构造解释AI行为。然后，我们证明当今许多XAI方法可以在定性评估中映射到行为的民间概念。这使我们能够揭示阻碍当前方法成功解释的失败模式——即任何给定XAI方法所缺失的信息构造，而包含这些构造可以降低误解AI行为的可能性。
英文摘要：
We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.
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。
