Subliminal Learning Is Steering Vector Distillation

This research explores subliminal learning, a phenomenon where a student language model inherits behavioral traits from a teacher model even when trained on semantically unrelated data. The authors demonstrate that this process is driven by steering vector distillation, where the teacher’s system prompt acts as a linear direction in activation space that the student internalizes during fine-tuning. By extracting and manipulating these steering vectors, the study shows they are both necessary and sufficient for transmitting traits like specific personality biases or preferences. The findings explain that subliminal learning often fails between different model families because these activation directions are highly model-specific. Furthermore, the researchers identify that adaptive optimizers and low-rank training are essential for the student to successfully capture these subtle signals. Ultimately, the work provides a mechanistic framework for understanding how non-semantic data can unexpectedly alter a model's high-level behavior.