Llama 3
Meta
partial detail 8 method fields published
Evaluation
Adversarial testing: multilingual
Red teaming of multilingual risks: language mixing in prompts, lower-resource language attacks (limited safety finetuning data/generalization), and slang/cultural-specific references
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.