Explanations Can Reduce Overreliance on AI Systems During Decision-Making

Author:

Vasconcelos Helena1ORCID,Jörke Matthew1ORCID,Grunde-McLaughlin Madeleine2ORCID,Gerstenberg Tobias1ORCID,Bernstein Michael S.1ORCID,Krishna Ranjay2ORCID

Affiliation:

1. Stanford University, Stanford, CA, USA

2. University of Washington, Seattle, WA, USA

Abstract

Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI produces explanations for its predictions, compared to only providing predictions. Some have argued that overreliance results from cognitive biases or uncalibrated trust, attributing overreliance to an inevitability of human cognition. By contrast, our paper argues that people strategically choose whether or not to engage with an AI explanation, demonstrating empirically that there are scenarios where AI explanations reduce overreliance. To achieve this, we formalize this strategic choice in a cost-benefit framework, where the costs and benefits of engaging with the task are weighed against the costs and benefits of relying on the AI. We manipulate the costs and benefits in a maze task, where participants collaborate with a simulated AI to find the exit of a maze. Through 5 studies (N = 731), we find that costs such as task difficulty (Study 1), explanation difficulty (Study 2, 3), and benefits such as monetary compensation (Study 4) affect overreliance. Finally, Study 5 adapts the Cognitive Effort Discounting paradigm to quantify the utility of different explanations, providing further support for our framework. Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.

Funder

Snap Inc.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Human-Computer Interaction,Social Sciences (miscellaneous)

Reference99 articles.

1. Julia Angwin , Jeff Larson , Surya Mattu , and Lauren Kirchner . 2016. Machine bias . In Ethics of Data and Analytics . Auerbach Publications , 254--264. Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias. In Ethics of Data and Analytics. Auerbach Publications, 254--264.

2. Yuichiro Anzai and Herbert A Simon . 1979. The theory of learning by doing. Psychological review 86, 2 ( 1979 ), 124. Yuichiro Anzai and Herbert A Simon. 1979. The theory of learning by doing. Psychological review 86, 2 (1979), 124.

3. Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

4. Gagan Bansal , Tongshuang Wu , Joyce Zhou , Raymond Fok , Besmira Nushi , Ece Kamar , Marco Tulio Ribeiro, and Daniel S. Weld . 2021 . Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance . arXiv:2006.14779 [cs.AI] Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, and Daniel S. Weld. 2021. Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance. arXiv:2006.14779 [cs.AI]

5. Bernard Barber. 1983. The logic and limits of trust. (1983). Bernard Barber. 1983. The logic and limits of trust. (1983).

Cited by 48 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