#machine learning
Dec 2025
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
This work proposes a training-free method that operates directly on the LLM internal representations, leveraging prior evidence that decision-relevant information is encoded within them, and derives policy-violation scores directly from normalized representations of LLM hidden activations.
Oren Rachmil, Roy Betser, Itay Gershon et al.
· arXiv.org · 5 citations
· ⚡1