meta-llama/Llama-Guard-3-8B
Text Generation
•
8B
•
Updated
•
32.1k
•
•
260
Agent Safety & Alignment
AI agent security: prompt injection defense, jailbreak detection, guardrails, constitutional AI, zero trust architecture.
Note Content moderation model
-
Jailbroken: How Does LLM Safety Training Fail?
Paper • 2307.02483 • Published • 14 -
Constitutional AI: Harmlessness from AI Feedback
Paper • 2212.08073 • Published • 4 -
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Paper • 2312.06674 • Published • 8 -
Language Models (Mostly) Know What They Know
Paper • 2207.05221 • Published • 1 -
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
Paper • 2511.22570 • Published • 87