SOURCE-LINKED INTELLIGENCE

Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses people prefer from an AI need not be the responses they themselves would give. We distinguish alignment with human preferences from alignment with human behavior, and show that alignment with human preferences can make model behavior less human-like even when both preferences and responses come entirely from humans. We call this the Turing-test gap. We show that preference alignment preserves the human response distribution only under a restrictive

Read original source ↗ Open in workspace

recordType

paper

region

Global