Skip to content
conftrace_

refusal suppression

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

safety alignment (3) large language model (2) latent space direction (1) activation space (1) self-organizing map (1) attack success rate (1) model ablation (1) jailbreak attack (1) mechanistic interpretability (1) language model (1)

Papers

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026 Don’t Say No: Jailbreaking LLM by Suppressing Refusal ACL 2025 Jailbreak Attack Initializations as Extractors of Compliance Directions EMNLP 2025