pith. sign in

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 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Adaptive Probe-based Steering for Robust LLM Jailbreaking

cs.CR · 2026-05-19 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Adaptive Probe-based Steering for Robust LLM Jailbreaking cs.CR · 2026-05-19 · unverdicted · none · ref 32

    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.