Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference, a phenomenon known as subliminal learning. Prior work has identified several parts of this process. How the signal builds up during training and produces behavioral transfer remains unclear, making targeted mitigation difficult. We propose and validate trait-direction drift as a mechanism for subliminal learning: biased generation creates measurable preference gaps in teacher data, and student-recognizable gaps induce ...
| Authors | Zhixuan Liu, Zhichen Dong, Yuyu Fan et al. |
|---|---|
| Primary category | cs.LG |
| Published | 1 September 2026 |
| Last updated at source | 12 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.