摘要
In AI-assisted decision-making, it is critical for human decision-makers to know when to trust AI and when to trust themselves. However, prior studies calibrated human trust only based on AI confdence indicating AI's correctness likelihood (CL) but ignored humans' CL, hindering optimal team decision-making. To mitigate this gap, we proposed to promote humans' appropriate trust based on the CL of both sides at a task-instance level. We frst modeled humans' CL by approximating their decision-making models and computing their potential performance in similar instances. We demonstrated the feasibility and efectiveness of our model via two preliminary studies. Then, we proposed three CL exploitation strategies to calibrate users' trust explicitly/implicitly in the AI-assisted decision-making process. Results from a between-subjects experiment (N=293) showed that our CL exploitation strategies promoted more appropriate human trust in AI, compared with only using AI confdence. We further provided practical implications for more human-compatible AI-assisted decision-making.
学科与关键词
- Understanding the influence of AI autonomy on AI explainability levels in human-AI teams using a mixed methods approachHauptman, Allyson I.*; Schelble, Beau G.; Duan, Wen; Flathmann, Christopher; Mcneese, Nathan J.Cognition Technology & Work, 2024, 26(3): 435-455.
- I Know This Looks Bad, But I Can Explain: Understanding When AI Should Explain Actions In Human-AI TeamsZhang, Rui*; Flathmann, Christopher; Musick, Geoff; Schelble, Beau; McNeese, Nathan J.; Knijnenburg, Bart; Duan, WenACM Transactions on Interactive Intelligent Systems, 2024, 14(1): 6.被引 4
- How Being Outvoted by AI Teammates Impacts Human-AI CollaborationHu, Mo; Zhang, Guanglu; Chong, Leah; Cagan, Jonathan; Goucher-Lambert, Kosa*International Journal of Human-Computer Interaction, 2024.
