Adaptive probe-based steering guided by model extraction and activation statistics improves LLM jailbreak success rates from 6% to 70% average harmfulness without extra contrastive prompts or manual tuning.
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Probe-based Steering for Robust LLM Jailbreaking
Adaptive probe-based steering guided by model extraction and activation statistics improves LLM jailbreak success rates from 6% to 70% average harmfulness without extra contrastive prompts or manual tuning.