Performance and Metacognition Disconnect when Reasoning in Human-AI Interaction

TL;DR

This study investigates how users' self-assessment of performance in human-AI tasks often overestimates actual ability, revealing a disconnect between confidence and accuracy influenced by AI literacy and metacognitive factors.

Contribution

It demonstrates that AI use can impair metacognitive accuracy, with higher AI literacy linked to less accurate self-assessment, and introduces a computational model explaining these effects.

Findings

Participants overestimated their performance by four points.

Higher AI literacy correlated with less accurate self-assessment.

The Dunning-Kruger effect was absent with AI assistance.

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.