Refusal suppression via difference-in-means ablation equals projection onto a linear probe's decision boundary, and a controlled evasion attack optimizing confidence past the boundary achieves SOTA success rates on 15 models.
Latent-space Attacks for Refusal Evasion in Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent-space Attacks for Refusal Evasion in Language Models
Refusal suppression via difference-in-means ablation equals projection onto a linear probe's decision boundary, and a controlled evasion attack optimizing confidence past the boundary achieves SOTA success rates on 15 models.