Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

要旨

Many researchers motivate explainable AI with studies showing that human-AI team performance on decision-making tasks improves when the AI explains its recommendations. However, prior studies observed improvements from explanations only when the AI, alone, outperformed both the human and the best team. Can explanations help lead to complementary performance, where team accuracy is higher than either the human or the AI working solo? We conduct mixed-method user studies on three datasets, where an AI with accuracy comparable to humans helps participants solve a task (explaining itself in some conditions). While we observed complementary improvements from AI augmentation, they were not increased by explanations. Rather, explanations increased the chance that humans will accept the AI's recommendation, regardless of its correctness. Our result poses new challenges for human-centered AI: Can we develop explanatory approaches that encourage appropriate trust in AI, and therefore help generate (or improve) complementary performance?

著者
Gagan Bansal
University of Washington, Seattle, Washington, United States
Tongshuang Wu
University of Washington, Seattle, Washington, United States
Joyce Zhou
University of Washington, Seattle, Washington, United States
Raymond Fok
University of Washington, Seattle, Washington, United States
Besmira Nushi
Microsoft Research, REDMOND, Washington, United States
Ece Kamar
Microsoft Research, Redmond, Washington, United States
Marco Tulio Ribeiro
Microsoft Research, Redmond, Washington, United States
Daniel Weld
University of Washington, Seattle, Washington, United States
DOI

10.1145/3411764.3445717

論文URL

https://doi.org/10.1145/3411764.3445717

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Computational AI Development and Explanation

[B] Paper Room 02, 2021-05-14 01:00:00~2021-05-14 03:00:00 / [C] Paper Room 02, 2021-05-14 09:00:00~2021-05-14 11:00:00 / [A] Paper Room 02, 2021-05-13 17:00:00~2021-05-13 19:00:00
Paper Room 02
12 件の発表
2021-05-14 01:00:00
2021-05-14 03:00:00
日本語まとめ
読み込み中…