With the increasing use of AI, recent research in human–computer interaction explores Explainable AI (XAI) to make AI advice more interpretable. While research addresses the effects of incorrect AI advice on AI-assisted decision-making, the impact of incorrect explanations is neglected so far. Additionally, recent work shows that not only different explanation modalities impact decision-makers, but also human factors play a critical role. To analyze relevant phenomena influencing AI-assisted decision-making, this work explores the impacting factors by conceptualizing theories of appropriate reliance and taking the first steps toward empirical evidence. We show that humans’ reliance on AI and the human–AI team performance are impacted by imperfect XAI in a study with 136 participants. Additionally, we find that cognitive styles affect decision-making in different explanation modalities. Hence, we shed light on diverse factors that impact human–AI collaboration and provide guidelines for designers to tailor such human–AI collaboration systems to individuals’ needs.

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.

Advances in artificial intelligence have enabled unprecedented technical capabilities, yet making these advances useful in the real world remains challenging. We engaged in a Research through Design process to improve the ideation of AI products and services. We developed a design resource capturing AI capabilities based on 40 AI features commonly used across various domains. To probe its usefulness, we created a set of slides illustrating AI capabilities and asked designers to ideate AI-enabled user experiences. We also incorporated capabilities into our own design process to brainstorm concepts with domain experts and data scientists. Our research revealed that designers should focus on innovations where moderate AI performance creates value. We reflect on our process and discuss research implications for creating and assessing resources to systematically explore AI’s problem-solution space.

To enable the development and use of safe and equitable artificial intelligence (AI) systems, AI engineers must monitor deployed AI systems and learn from past AI incidents where failures have occurred. Around the world, public databases for cataloging AI systems and resulting harms are instrumental in promoting awareness of potential AI harms among policymakers, researchers, and the public. However, despite growing recognition of the potential of AI systems to produce harms, causes of AI systems failure remain elusive and AI incidents continue to occur. For example, incidents of AI bias are frequently reported and discussed, yet biased systems continue to be developed and deployed.