liveBook · Manning

Llama Guard

As explained in AI Governance

Llama Guard is a language-model-based safety classifier that evaluates content against defined safety categories.

Llama Guard is a language-model-based safety classifier. It served as an output classifier after domain fine-tuning degraded safety on sensitive topics; the team retained the adaptation and added the safeguard. They also ran Garak before deployment and before each later fine-tuning cycle, treating evaluation as a gate. section 4.9 section 4.9

How AI Governance covers it

How deep it goes
Describes its role as an output classifier but does not detail its internals or configuration.
Examples
Uses degraded safety on sensitive topics after domain fine-tuning as the reason to add the classifier.
What you can do after
Apply Llama Guard as an output classifier when fine-tuning weakens safety.
How it connects
Links Llama Guard to fine-tuning, safety alignment, and Garak evaluation.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.