Subliminal Steering: Stronger Encoding of Hidden Signals

arXiv:2604.25783v2 Announce Type: replace Abstract: Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open questions about the scope of signals it can transfer, the mechanisms that explain it, and the precision with which a bias can be encoded. We tackle these problems by introducing subliminal steering, a variant of subliminal learning in which the teacher's bias is implemented not via a system prompt, as in prior work, but through a steering vector trained to maximize the likelihood of a set of target samples. First, we show that subliminal steering transfers complex multi-word biases, whereas prior work focused on single-word preferences, demonstrating a large scope of subliminally transferable signals. Moreover, the transfer is reliable enough to appear in settings previously thought not to exhibit subliminal learning, including plain SGD (not just Adam), full fine-tuning (not just LoRA), and models such as Llama and Phi. Second, we provide mechanistic evidence that subliminal learning transfers not only the target behavioral bias, but also the steering vector itself, localized to the layers at which the teacher was steered. Finally, we show that the bias is encoded with such precision that a new steering vector trained on the subliminally-laden dataset attains high cosine similarity with the original vector.

Abstract:Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open questions about the scope of signals it can transfer, the mechanisms that explain it, and the precision with which a bias can be encoded. We tackle these problems by introducing subliminal steering, a variant of subliminal learning in which the teacher's bias is implemented not via a system prompt, as in prior work, but through a steering vector trained to maximize the likelihood of a set of target samples. First, we show that subliminal steering transfers complex multi-word biases, whereas prior work focused on single-word preferences, demonstrating a large scope of subliminally transferable signals. Moreover, the transfer is reliable enough to appear in settings previously thought not to exhibit subliminal learning, including plain SGD (not just Adam), full fine-tuning (not just LoRA), and models such as Llama and Phi. Second, we provide mechanistic evidence that subliminal learning transfers not only the target behavioral bias, but also the steering vector itself, localized to the layers at which the teacher was steered. Finally, we show that the bias is encoded with such precision that a new steering vector trained on the subliminally-laden dataset attains high cosine similarity with the original vector.

Computation and Language (cs.CL)

arXiv:2604.25783 [cs.CL]

(or arXiv:2604.25783v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2604.25783 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Subliminal Steering: Stronger Encoding of Hidden Signals

Subiecte conexe