Evaluating Actionability in Explainable AI
Preprint
Abstract
A core assumption of Explainable AI (XAI) is that explanations are useful to users -- that is, users will do something with the explanations. Prior work, however, does not clearly connect the information provided in explanations to user actions to evaluate effectiveness. In this paper, we articulate this connection. We conducted a formative study through 14 interviews with end users in education and medicine. We contribute a catalog of information and associated actions. Our catalog maps 12 categories of information that participants described relying on to take 60 different actions. We show how AI Creators can use the catalog's specificity and breadth to articulate how they expect information in their explanations to lead to user actions and test their assumptions. We use an exemplar XAI system to illustrate this approach. We conclude by discussing how our catalog expands the design space for XAI systems to support actionability.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- The Concept of Agency in the Era of Artificial Intelligence: Dimensions and DegreesInformation Systems Frontiers, 2022
- Enhancing human agency through redress in Artificial Intelligence SystemsAI & SOCIETY, 2022
- Agency in augmented reality: exploring the ethics of Facebook’s AI-powered predictive recommendation systemAI and Ethics, 2022
- Varieties of transparency: exploring agency within AI systemsAI & SOCIETY, 2022
- Actionable Content Discovery for Healthcare2021
- Group Agency and Artificial IntelligencePhilosophy & Technology, 2021
- Artificial intelligence in education: The three paradigmsComputers and Education: Artificial Intelligence, 2021
- Explanation Ontology: A Model of Explanations for User-Centered AI2020
- Conclusion: Mobility, Data and Learner Agency in Networked Learning2020
- Artificial Intelligence, Responsibility Attribution, and a Relational Justification of ExplainabilityScience and Engineering Ethics, 2019