Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations
This work addresses the problem of how decision-makers can effectively use imperfect AI advice, providing foundational concepts for analyzing reliance behavior and designing AI advisors, though it is incremental in building on existing research gaps.
The paper tackles the lack of a common definition and measurement for appropriate reliance on AI advice, proposing a two-dimensional concept called Appropriateness of Reliance (AoR) and testing it with 200 participants to show how explanations affect reliance and advice effectiveness.
AI advice is becoming increasingly popular, e.g., in investment and medical treatment decisions. As this advice is typically imperfect, decision-makers have to exert discretion as to whether actually follow that advice: they have to "appropriately" rely on correct and turn down incorrect advice. However, current research on appropriate reliance still lacks a common definition as well as an operational measurement concept. Additionally, no in-depth behavioral experiments have been conducted that help understand the factors influencing this behavior. In this paper, we propose Appropriateness of Reliance (AoR) as an underlying, quantifiable two-dimensional measurement concept. We develop a research model that analyzes the effect of providing explanations for AI advice. In an experiment with 200 participants, we demonstrate how these explanations influence the AoR, and, thus, the effectiveness of AI advice. Our work contributes fundamental concepts for the analysis of reliance behavior and the purposeful design of AI advisors.