conftrace_

safety benchmark

32 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (19) safety evaluation (7) jailbreak attack (6) ai safety (6) benchmark evaluation (6) diffusion model (4) llm safety (3) risk assessment (3) vision-language model (3) model safety (3)

Papers

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? NeurIPS 2024 SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models ACL 2024 T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models NeurIPS 2024 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024 Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark NeurIPS 2023