Llama Guard: Meta’s Open Safety Classifier for AI Guardrails

Research question

Can an instruction-tuned LLM serve as a customisable content-safety classifier?

Key findings

A Llama 2-7B classifier with a safety taxonomy outperforms OpenAI moderation and Perspective API on benchmarks - Zero-shot adaptable to new policies

Sources

arxiv.orghttps://arxiv.org/abs/2312.06674

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

StyleAT: Defending Face Recognition Against Semantic Attacks

With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models remain acutely vulnerable to adversarial semantic edits. I.e.,…

Guardrails and classifier defences2026

Robot Visions: Breaking reCAPTCHA at Zero Cost and Zero Shot

Google reCAPTCHA is the most widely deployed visual CAPTCHA service, protecting hundreds of thousands of websites from automated bots. It serves as a critical line of defense against automated attacks, including…

Guardrails and classifier defences2026

The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs

We have developed the MAL Simulator, a cyber operation simulator based on the Meta Attack Language (MAL). The MAL Simulator is intended for decision-driven cyber attack and defense simulations, for system analysis…

Guardrails and classifier defences2026