Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions
This work addresses the problem of making explainable AI more actionable for users, but it is incremental as it builds on existing research without introducing new methods or data.
The paper tackles the gap between AI explanations and user actions by developing a framework that maps prior work on explanation information and associated user actions, uncovering gaps in the information presented to users.
A core assumption of explainable AI systems is that explanations change what users know, thereby enabling them to act within their complex socio-technical environments. Despite the centrality of action, explanations are often organized and evaluated based on technical aspects. Prior work varies widely in the connections it traces between information provided in explanations and resulting user actions. An important first step in centering action in evaluations is understanding what the XAI community collectively recognizes as the range of information that explanations can present and what actions are associated with them. In this paper, we present our framework, which maps prior work on information presented in explanations and user action, and we discuss the gaps we uncovered about the information presented to users.