conftrace_

safety moderation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) harmlessness annotation (1) refusal detection (1) prompt classification (1) llm safety (1) jailbreak detection (1) risk classification (1) preference data (1) human preference (1) reinforcement learning from human feedback (1)

Papers

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference ACL 2025 WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs NeurIPS 2024