Subliminal Learning is a LoRA Artifact

Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning. While qualitative evidence supports the existence of this effect, its magnitude has not been systematically characterized. This study quantifies subliminal behavioral transfer ratios by steering two teacher models (Llama-2-7B-Chat and Qwen2.5-7B-Instruct) at varying steering strengths and distilling student models using only benign data. Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors. Llama-2 demonstrates a sharp threshold ($τ= {0.25,0.32} \ \text{beyond} \ α= -0.15$), whereas Qwen2.5 displays continuous and higher levels of transfer ($τ$ up to $0.61$).

Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models. It allows the transfer of a bias or behavior from a teacher model to a student by distilling from seemingly unrelated or random synthetic data from the teacher. This presents challenges in ensuring AI systems remain predictable and are trained safely, as standard auditing of the input data would not catch the hidden subliminal signal. Here, we investigate several open questions as to the enabling mechanisms and drivers of SL. First is the nature of the process by which biases are encoded in the data. We find that by adding Gaussian noise to the weights of the teacher and student models, the magnitude of subliminal transfer is increased by a factor of 1.9 in Gemma and 1.3 in Llama, suggesting that non-semantic weight structures play a crucial role. We show that steering vectors can be applied to the teacher to produce subliminal data, in addition to prompting and finetuning as used in previous studies. Analysis of the activations of the student models that have been trained on steered and prompted data demonstrates that students inherit not just the semantic meaning of the teacher's bias, but also the type of intervention that was used to apply it: steered students imitate steering vectors, prompted students do not. Additionally, the gradients of steered subliminal data show a linear correlation with the teacher's steering vectors, showing promise for data auditing. More broadly, as synthetic data becomes central to frontier training pipelines, being able to see the latent signals hidden in training data becomes paramount.

Subliminal learning refers to a student language model acquiring a teacher's traits (e.g. a system-prompted preference for owls) when fine-tuned on the teacher's outputs, despite the outputs being semantically unrelated to those traits. It remains poorly understood how data without semantic meaning can transfer specific semantic traits. In this work, we show that subliminal learning is mediated by a single steering vector, i.e. a vector added to the model's activations. Across two open-source models, we find that the teacher's system prompt is well approximated by a steering vector, and that the student's behavior is driven by learning an aligned vector over fine-tuning. System prompts that are not well approximated by steering vectors are not subliminally learned. This is a special case of steering vector distillation, in which a student trained on the outputs of a steered teacher learns to imitate that steering. We demonstrate steering vector distillation on a range of semantic and random vectors. Adding a semantic vector to a model's activations can have both model-independent and model-specific (i.e. non-semantic) effects on its behavior, so generated data that is non-semantic can transmit a vector with semantic effects, enabling subliminal learning. This also explains why subliminal learning does not transfer between models. We find that adaptive optimizers are necessary for subliminal learning in language models: activation gradients on steered data carry a small but consistent component along the steering direction, and non-adaptive optimizers impede this by allowing outlier gradients to dominate.