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
Read the official announcement
Opens arxiv.org
More from arXiv: cs.AI preprints
- Human-AI Mutualism Is Unstable under Capability Asymmetry20 November 2026
- Training Language Models for Introspective Oversight20 November 2026
- Where the Tokens Go: Heat, Entropy and Error in Agentic Coding20 November 2026
- HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs20 November 2026
- RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding20 November 2026
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.