Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
PRISM: Recovering Instruction Sets from Language Model Activations
Gilad Gressel, Rahul Pankajakshan, Julia Diament +3
As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior. This is difficult when models in…
cs.AI2026
GAVEL: Towards Rule-Based Safety Through Activation Monitoring
Shir Rozenfeld, Rahul Pankajakshan, Itay Zloczower +3
Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. Ho…