AWhat changed
Trained reasoning models to internalize explicit safety specifications through specification-referencing synthetic supervision followed by reinforcement learning, reporting better jailbreak resistance and less overrefusal on the evaluated tasks.
Scientific scope
Trained reasoning models to internalize explicit safety specifications through specification-referencing synthetic supervision followed by reinforcement learning, reporting better jailbreak resistance and less overrefusal on the evaluated tasks. No universal safety, faithful reasoning or jailbreak-immunity guarantee. Human-written policies and prompt-category information remain inputs even though human-written chains of thought and answers are not required.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. No universal safety, faithful reasoning or jailbreak-immunity guarantee. Human-written policies and prompt-category information remain inputs even though human-written chains of thought and answers are not required.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Deliberative Alignment: Reasoning Enables Safer Language Models
- Guan et al.: policy-reasoning deliberative alignment — company research account
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction