AI RESEARCH
Aligning to Illusions: Choice Blindness in Human and AI Feedback
arXiv CS.CL
•
ArXi:2603.08412v1 Announce Type: new Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of surreptitiously swapped preferences go undetected, extending choice blindness to third-person evaluative comparison of unfamiliar text.