ψpsychologyof.ai
Research/Human-AI Teams/Paper
2021·CHI Conference on Human Factors in Computing Systems

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D.

🧩 Human-AI Teams

Abstract

Tests whether AI explanations help human-AI teams exceed the performance of either alone. Surprisingly, explanations that increase understanding do not always improve team performance — and can even hurt it by inducing over-reliance.

Key Findings

  • AI explanations improve human understanding but not necessarily team performance
  • Explanations can induce over-reliance when the AI is wrong
  • Complementary performance requires humans to know when to override the AI

Source

DOI: 10.1145/3411764.3445717 →

Related Papers

2019·FAccT Conference on Fairness, Accountability, and Transparency

On Human Predictions with Explanations and Predictions of Machine Learning Models

Lai, V., & Tan, C.

collaboration→
2023·CHI Conference on Human Factors in Computing Systems

Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems

Gaube, S., Suresh, H., Raber, M., Merz, E. M., Ghassemi, M., & Gurkan, H.

collaboration→