Don't Be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration

Authors: P Spitzer, J Holstein, K Morrison

Published: 2025

Publication: ... Journal of Human ..., 2025 - Taylor & Francis

Incorrect explanations in AI-assisted decision-making lead to a misinformation effect, negatively impacting human reasoning, procedural knowledge, and collaboration performance.

Methods: A study on human-AI collaboration involving AI-supported decision-making paired with explainable AI (XAI) to assess the effects of incorrect explanations.

Key Findings: Impact of incorrect explanations on human reasoning strategies, procedural knowledge, and team performance in human-AI collaboration.

Limitations: Limited exploration of long-term effects of incorrect explanations and generalizability across diverse AI systems or domains.

Institution: Karlsruhe Institute of Technology, Carnegie Mellon University, University of Bayreuth

Research Area: Human-AI Collaboration, Explainable AI (XAI)

Discipline: Human-Computer Interaction (HCI)

Sample Size: 160 participants

Citations: 13