Authors: L S. Treiman, CJ Ho, W Kool
Year: 2025
Published in: Proceedings of the 2025 ACM Conference ..., 2025 - dl.acm.org
Institution: Washington University in St. Louis, National Cheng Kung University
Research Area: Human-AI Interaction, Cognitive Science, Behavioral Research in AI Training
Discipline: Human-Computer Interaction (HCI), Behavioral Science
Participants tend to rely on intuition (fast thinking) rather than deliberation (slow thinking) when training AI agents in the ultimatum game, impacting human-AI collaboration system design.
Methods: Participants trained an AI agent in the ultimatum game to analyze whether their training decisions aligned more with intuitive or deliberative cognitive processes.
Key Findings: The cognitive processes (fast vs. slow thinking) underlying human decision-making during AI training.
DOI: https://dl.acm.org/doi/abs/10.1145/3715275.3732177
Citations: 1