The Llama 3 Herd of Models

Meta, 2024, The Llama 3 Herd of Models (arXiv preprint arXiv:2407.21783)

Subscriber deck — free during early access

1 cards in “5.4.8 Limitations” · whole deck

5.4.8 Limitations

What safety limitations do the Llama 3 authors acknowledge?
No testing can find every risk: the models may still produce harmful content, especially in languages other than English or under skilled adversarial prompting, and new jailbreaks will be found; they release system-level safety tools (such as Llama Guard 3) for developers.
- Meta, 2024, The Llama 3 Herd of Models (arXiv preprint arXiv:2407.21783), §5.4.8

Source

Llama Team, AI @ Meta. 2024. The Llama 3 Herd of Models. In arXiv preprint arXiv:2407.21783. https://arxiv.org/abs/2407.21783