Comparing Zealous and Restrained AI Recommendations in a Real-World Human-AI Collaboration Task

TL;DR

This study compares zealous and restrained AI assistance in a real-world video anonymization task, showing zealous AI improves recall and efficiency, but restrained AI can negatively impact human training.

Contribution

It provides empirical insights into how different AI recommendation strategies affect human-AI collaboration performance in a complex task.

Findings

Zealous AI reduces task completion time and increases recall.

Restrained AI can negatively influence human annotator training.

AI assistance strategies significantly impact team performance in recall-critical tasks.

Abstract

When designing an AI-assisted decision-making system, there is often a tradeoff between precision and recall in the AI's recommendations. We argue that careful exploitation of this tradeoff can harness the complementary strengths in the human-AI collaboration to significantly improve team performance. We investigate a real-world video anonymization task for which recall is paramount and more costly to improve. We analyze the performance of 78 professional annotators working with a) no AI assistance, b) a high-precision "restrained" AI, and c) a high-recall "zealous" AI in over 3,466 person-hours of annotation work. In comparison, the zealous AI helps human teammates achieve significantly shorter task completion time and higher recall. In a follow-up study, we remove AI assistance for everyone and find negative training effects on annotators trained with the restrained AI. These findings and our analysis point to important implications for the design of AI assistance in recall-demanding scenarios.