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

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.

Accepted to ACM CSCW 2024. 27 pages, 9 figures, 1 table, additional figures/table in the appendix

References in corpus (8)

• Seeing biodiversity: perspectives in machine learning for wildlife conservation
• Interactive and Explainable Region-guided Radiology Report Generation
• "Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
• Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations
• A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making
• Improving Human-AI Collaboration With Descriptions of AI Behavior
• Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
• The effectiveness of feature attribution methods and its correlation with automatic evaluation scores