In six small open-weight LLMs, jailbreak prompts are linearly separable in last-token embeddings by surface form, but not by refusal/compliance behavior.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometric Configurations of Perturbed Jailbreak Prompts
In six small open-weight LLMs, jailbreak prompts are linearly separable in last-token embeddings by surface form, but not by refusal/compliance behavior.