Beyond Predictions: A Study of AI Strength and Weakness Transparency Communication on Human-AI Collaboration

TL;DR

This study explores how AI communication about its strengths and weaknesses affects human-AI collaboration, showing that transparent explanations improve trust and task performance in decision-making tasks.

Contribution

The paper introduces a method for AI to communicate its strengths and limitations using decision tree-based explanations, enhancing human-AI teamwork.

Findings

AI performance insights improve task accuracy

Transparency about AI weaknesses boosts trust calibration

Effective communication enhances human-AI collaboration

Abstract

The promise of human-AI teaming lies in humans and AI working together to achieve performance levels neither could accomplish alone. Effective communication between AI and humans is crucial for teamwork, enabling users to efficiently benefit from AI assistance. This paper investigates how AI communication impacts human-AI team performance. We examine AI explanations that convey an awareness of its strengths and limitations. To achieve this, we train a decision tree on the model's mistakes, allowing it to recognize and explain where and why it might err. Through a user study on an income prediction task, we assess the impact of varying levels of information and explanations about AI predictions. Our results show that AI performance insights enhance task performance, and conveying AI awareness of its strengths and weaknesses improves trust calibration. These findings highlight the importance of considering how information delivery influences user trust and reliance in AI-assisted decision-making.