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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Morrison, Katelyn, Spitzer, Philipp, Turri, Violet, Feng, Michelle, Kühl, Niklas, Perer, Adam
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917660473688064
author Morrison, Katelyn
Spitzer, Philipp
Turri, Violet
Feng, Michelle
Kühl, Niklas
Perer, Adam
author_facet Morrison, Katelyn
Spitzer, Philipp
Turri, Violet
Feng, Michelle
Kühl, Niklas
Perer, Adam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_13566
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Impact of Imperfect XAI on Human-AI Decision-Making
Morrison, Katelyn
Spitzer, Philipp
Turri, Violet
Feng, Michelle
Kühl, Niklas
Perer, Adam
Human-Computer Interaction
Artificial Intelligence
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.
title The Impact of Imperfect XAI on Human-AI Decision-Making
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2307.13566