Slmguard

Chat with our AI to analyze and discuss Islamophobia-related content

How it works: When you send a message, our system analyzes it using two approaches:

Llama Guard: A specialized AI that detects harmful content
Taarruf Taxonomy: A framework designed specifically to identify Islamophobic patterns and harmful rhetoric against Muslims

What the results mean:

Red highlight: Taarruf Taxonomy detected Islamophobic content
Yellow highlight: Llama Guard detected potentially harmful content

Try a preset prompt

Slmguard — Conversation

Hello — I'm Slmguard, an AI assistant trained to help analyze content related to Islamophobia and Project Taarruf. Ask about detecting Islamophobic content, its patterns, or how to use the taxonomy for moderation.

12:03 PM