mmathys/openai-moderation-api-evaluation
Viewer • Updated • 1.68k • 820 • 38
moderation-prompts
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 29.8k • 1.82k -
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Paper • 2406.18495 • Published • 15 -
ShieldGemma: Generative AI Content Moderation Based on Gemma
Paper • 2407.21772 • Published • 15 -
lmsys/lmsys-chat-1m
Viewer • Updated • 1M • 6.21k • 937 -
PKU-Alignment/BeaverTails
Viewer • Updated • 364k • 19k • 110 -
AgentPublic/camembert-base-toxic-fr-user-prompts
Text Classification • 0.1B • Updated • 6 • 8 -
OpenSafetyLab/Salad-Data
Viewer • Updated • 30.4k • 1.79k • 31 -
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 235k • • 309 -
davanstrien/aart-ai-safety-dataset
Viewer • Updated • 3.27k • 10 • 2 -
walledai/AdvBench
Viewer • Updated • 520 • 12.1k • 105