Llama Guard 3

'Llama Guard 3' is a benchmark used to evaluate the safety refusal rates of Large Language Models (LLMs) in response to harmful requests.

Papers using Llama Guard 3 (3)

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection2025 · 1 citesTurning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection2025 · 1 citesX-Guard: Multilingual Guard Agent for Content Moderation2025