conftrace_

refusal detection

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

safety moderation (1) large language model (1) prompt classification (1) activation steering (1) llm safety (1) jailbreak detection (1) risk classification (1) cosine similarity (1) safety alignment (1) model interpretability (1)

Papers

COSMIC: Generalized Refusal Direction Identification in LLM Activations ACL 2025 WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs NeurIPS 2024