Improving Human-AI Collaboration With Descriptions of AI Behavior

TL;DR

Providing users with descriptions of AI behavior on specific subgroups enhances human-AI collaboration by improving decision accuracy and appropriate reliance across multiple domains.

Contribution

This study demonstrates that behavior descriptions of AI systems can significantly improve human-AI decision-making by fostering better mental models and reliance.

Findings

Behavior descriptions help identify AI failures.

They increase reliance when AI is more accurate.

Overall, improve human-AI decision accuracy.

Abstract

People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior descriptions, details of how AI systems perform on subgroups of instances. We tested the efficacy of behavior descriptions through user studies with 225 participants in three distinct domains: fake review detection, satellite image classification, and bird classification. We found that behavior descriptions can increase human-AI accuracy through two mechanisms: helping people identify AI failures and increasing people's reliance on the AI when it is more accurate. These findings highlight the importance of people's mental models in human-AI collaboration and show that informing people of high-level AI behaviors can significantly improve AI-assisted decision making.