pith. sign in

Refusal in Language Models Is Mediated by a Single Direction , booktitle =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.CR 1

years

2026 2

verdicts

UNVERDICTED 2

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 2 of 2 citing papers.