Using AI Uncertainty Quantification to Improve Human Decision-Making

TL;DR

This paper demonstrates that high-quality AI uncertainty quantification (UQ) can enhance human decision-making by providing probabilistic information, with experiments showing consistent benefits over AI predictions alone.

Contribution

It is the first to empirically evaluate the impact of calibrated, instance-level UQ on human decision-making across different probabilistic representations.

Findings

UQ improves decision-making performance compared to AI predictions alone

UQ benefits generalize across various probabilistic representations

High-quality, calibrated UQ can enhance real-world AI-human decision systems

Abstract

AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.