embedding-dynamics

Tag

Cards List
#embedding-dynamics

Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics

arXiv cs.AI · 2026-08-21 Cached

This paper presents a black-box method for LLM safety classification using dynamical systems and Koopman operators on prompt-response embedding dynamics to detect unsafe outputs.

0 favorites 0 likes
← Back to home

Submit Feedback