Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability

TL;DR

This paper critiques the reliance on subjective satisfaction in evaluating explainable AI, demonstrating that actionable explanations improve objective understanding even when user ratings do not differ from vacuous explanations.

Contribution

It introduces an experimental framework that distinguishes meaningful explanations from placebic ones and advocates for combining objective metrics with subjective surveys in XAI evaluation.

Findings

Participants with actionable explanations showed better mental models.

Subjective satisfaction ratings did not differ between explanation types.

Objective measures reveal the true effectiveness of explanations.

Abstract

Explainable AI (XAI) presents useful tools to facilitate transparency and trustworthiness in machine learning systems. However, current evaluations of system explainability often rely heavily on subjective user surveys, which may not adequately capture the effectiveness of explanations. This paper critiques the overreliance on user satisfaction metrics and explores whether these can differentiate between meaningful (actionable) and vacuous (placebic) explanations. In experiments involving optimal Social Security filing age selection tasks, participants used one of three protocols: no explanations, placebic explanations, and actionable explanations. Participants who received actionable explanations significantly outperformed the other groups in objective measures of their mental model, but users rated placebic and actionable explanations as equally satisfying. This suggests that subjective surveys alone fail to capture whether explanations truly support users in building useful domain understanding. We propose that future evaluations of agent explanation capabilities should integrate objective task performance metrics alongside subjective assessments to more accurately measure explanation quality. The code for this study can be found at https://github.com/Shymkis/social-security-explainer.