Evaluating the Influences of Explanation Style on Human-AI Reliance

TL;DR

This study investigates how different explanation styles in XAI, such as feature-based and example-based methods, influence human reliance on AI, emphasizing the importance of tailoring explanations to users and context.

Contribution

It provides empirical evidence on the distinct impacts of explanation styles on human-AI reliance, highlighting the need for context-aware explanation design.

Findings

Feature-based and example-based explanations influence reliance differently.

Explanation style effects vary with user performance and task complexity.

Adapting explanations to users and context is more effective than broad interpretability.

Abstract

Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the interpretability of complex model decisions. Despite the proliferation of proposed methods, there is mixed evidence surrounding the effects of different styles of XAI explanations on human-AI reliance. Interpreting these conflicting findings requires an understanding of the individual and combined qualities of different explanation styles that influence appropriate and inappropriate human-AI reliance, and the role of interpretability in this interaction. In this study, we investigate the influences of feature-based, example-based, and combined feature- and example-based XAI methods on human-AI reliance through a two-part experimental study with 274 participants comparing these explanation style conditions. Our findings suggest differences between feature-based and example-based explanation styles beyond interpretability that affect human-AI reliance patterns across differences in individual performance and task complexity. Our work highlights the importance of adapting explanations to their specific users and context over maximising broad interpretability.