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

Author:

Morrison Katelyn1ORCID,Spitzer Philipp2ORCID,Turri Violet3ORCID,Feng Michelle3ORCID,Kühl Niklas4ORCID,Perer Adam1ORCID

Affiliation:

1. Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, USA

2. Karlsruhe Service Research Institute, Karlsruhe Institute of Technology, Karlsruhe, Germany

3. Carnegie Mellon University, Pittsburgh, PA, USA

4. Information Systems and Human-Centric Artificial Inteligence, University of Bayreuth, Bayreuth, Germany

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.

Funder

National Heart, Lung, and Blood Institute of the National Institutes of Health

Publisher

Association for Computing Machinery (ACM)

Reference99 articles.

1. 2023. https://www.inaturalist.org/. Accessed: July 2, 2023.

2. 2023. https://merlin.allaboutbirds.org/. Accessed: July 2, 2023.

3. 2023. https://www.wildme.org/. Accessed: July 2, 2023.

4. 2023. https://www.allaboutbirds.org/guide/. Accessed: July 2, 2023.

5. Automated Bird Counting with Deep Learning for Regional Bird Distribution Mapping

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3