Impact of Model Interpretability and Outcome Feedback on Trust in AI

要旨

This paper bridges the gap in Human-Computer Interaction (HCI) research by comparatively assessing the effects of interpretability and outcome feedback on user trust and collaborative performance with AI. Through novel pre-registered experiments (N=1,511 total participants) using an interactive prediction task, we analyzed how interpretability and outcome feedback influence users’ task performance and trust in AI. The results counter the widespread belief that interpretability drives trust, showing that interpretability led to no robust improvements in trust and that outcome feedback had a significantly greater and more reliable effect. However, both factors had modest effects on participants’ task performance. These findings suggest that (1) interpretability may be less effective at increasing trust than factors like outcome feedback, and (2) augmenting human performance via AI systems may not be a simple matter of increasing trust in AI, as increased trust is not always associated with equally sizable performance improvements. Our exploratory analyses further delve into the mechanisms underlying this trust-performance paradox. These findings present an opportunity for research to focus not only on methods for generating interpretations but also on techniques that ensure interpretations impact trust and performance in practice.

著者
Daehwan Ahn
University of Georgia, Athens, Georgia, United States
Abdullah Almaatouq
MIT, Cambriedge, Massachusetts, United States
Monisha Gulabani
Amazon, Seattle, Washington, United States
Kartik Hosanagar
University of Pennsylvania, Philadelphia, Pennsylvania, United States
論文URL

https://doi.org/10.1145/3613904.3642780

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Algorithmic Trust and Censorship

315
5 件の発表
2024-05-16 20:00:00
2024-05-16 21:20:00