Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning

arXiv:2610.13536v1 Announce Type: cross Abstract: When a language model is distilled from a teacher that shares its base parameters, the student can inherit behavioural traits of the teacher---including misalignment---even from data that is semantically unrelated to the trait (Cloud et al., 2026). All existing defences require knowing the trait. We remove this requirement and prove that a subliminally transferred trait can be recovered from the parameter updates alone, without supervision, by exploiting a single asymmetry: the trait is expressed consistently across diverse datasets generated b

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.