FirsthandTech
arXiv: cs.AI preprintsInternational20 November 2026

Reading Human Preference from Looped Transformer Internal States

This is an official announcement record

Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2604.09870v3 Announce Type: replace-cross Abstract: Show a frozen language model two replies to the same request, one of which a person preferred. Can a small probe on the model's hidden states tell which? On Ouro-2.6B-Thinking, a model that runs its layers four times per token, and Anthropic's HH-RLHF data, the answer is yes, but only faintly. A linear probe picks the preferred reply 61.5% of the time, a small nonlinear network that scores each reply separately 64.9%, and the evaluator trained for version 1 reaches 64.7% on the test split: clearly better than simple rules such as pickin
Source: arXiv: cs.AI preprints

More from arXiv: cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.