Llama 2
Meta
partial detail 6 method fields published
Evaluation
Pretraining data audit: demographic representation of pronouns
Analysis of whether the Llama 2 pretraining corpus uses 'people' words in contexts more similar to 'men' than 'women' (following Bailey et al. 2022 and Ganesh et al. 2023)
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.