Performance and Metacognition Disconnect when Reasoning in Human-AI Interaction
Abstract
Optimizing human-AI interaction requires users to reflect on their own performance critically. Our paper examines whether people using AI to complete tasks can accurately monitor how well they perform. In Study 1, participants (N = 246) used AI to solve 20 logical problems from the Law School Admission Test. While their task performance improved by three points compared to a norm population, participants overestimated their performance by four points. Interestingly, higher AI literacy was linked to less accurate self-assessment. Participants with more technical knowledge of AI were more confident but less precise in judging their own performance. Using a computational model, we explored individual differences in metacognitive accuracy and found that the Dunning-Kruger effect, usually observed in this task, ceased to exist with AI. Study 2 (N = 452) replicates these findings. We discuss how AI levels metacognitive performance and consider consequences of performance overestimation for interactive AI systems enhancing cognition.
Cite
@article{arxiv.2409.16708,
title = {Performance and Metacognition Disconnect when Reasoning in Human-AI Interaction},
author = {Daniela Fernandes and Steeven Villa and Salla Nicholls and Otso Haavisto and Daniel Buschek and Albrecht Schmidt and Thomas Kosch and Chenxinran Shen and Robin Welsch},
journal= {arXiv preprint arXiv:2409.16708},
year = {2025}
}
Comments
27 pages, 10 figures, 6 tables