conftrace_

safety benchmark

27 papers

Explore in graph

Co-occurring keywords

large language model (13587) safety evaluation (94) ai safety (235) benchmark evaluation (1556) jailbreak attack (225) diffusion model (3751) llm safety (67) safety vulnerability (11) multilingual safety (11) language model safety (14)

Papers

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024
Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark NIPS 2023