The Impact of Imperfect XAI on Human-AI Decision-Making

TL;DR

This study investigates how imperfect explainable AI (XAI), which can provide incorrect explanations even when advice is correct, impacts human decision-making and collaboration, highlighting the importance of understanding and mitigating deception in AI explanations.

Contribution

The paper presents a comprehensive user study analyzing the effects of incorrect XAI explanations on human-AI decision-making, considering expertise and explanation assertiveness, and offers design guidelines.

Findings

Imperfect XAI influences reliance and team performance.

Humans' expertise level affects susceptibility to misleading explanations.

Incorrect explanations can deceive decision-makers during collaboration.

Abstract

Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility of the explanations being incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task, taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems.