Study on the Helpfulness of Explainable Artificial Intelligence
This addresses the problem of selecting effective XAI methods for critical domains like medical diagnostics, though it is incremental by focusing on user-centered evaluation.
The study tackled the challenge of evaluating Explainable AI (XAI) methods by proposing a user-centered approach that measures helpfulness through proxy tasks, showing differences in how state-of-the-art methods affect trust and decision-making accuracy.
Explainable Artificial Intelligence (XAI) is essential for building advanced machine learning-powered applications, especially in critical domains such as medical diagnostics or autonomous driving. Legal, business, and ethical requirements motivate using effective XAI, but the increasing number of different methods makes it challenging to pick the right ones. Further, as explanations are highly context-dependent, measuring the effectiveness of XAI methods without users can only reveal a limited amount of information, excluding human factors such as the ability to understand it. We propose to evaluate XAI methods via the user's ability to successfully perform a proxy task, designed such that a good performance is an indicator for the explanation to provide helpful information. In other words, we address the helpfulness of XAI for human decision-making. Further, a user study on state-of-the-art methods was conducted, showing differences in their ability to generate trust and skepticism and the ability to judge the rightfulness of an AI decision correctly. Based on the results, we highly recommend using and extending this approach for more objective-based human-centered user studies to measure XAI performance in an end-to-end fashion.