Pietro Lesci

pietrolesci

AI & ML interests

I like developing and applying causal methods to study the effect of training choices on models’ behaviour, including memorisation, shortcut learning, and tokenisation.

Recent Activity

updated a collection 3 days ago
Tokenisation-Bias
updated a dataset 3 days ago
pietrolesci/me-minipile-evals
published a dataset 3 days ago
pietrolesci/me-minipile-evals
View all activity

Organizations

EleutherAI's profile picture MilaNLP's profile picture Social Post Explorers's profile picture Training Dynamics's profile picture Hugging Face Discord Community's profile picture Unlearning's profile picture Info Tokenizers's profile picture co-evolve's profile picture