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

upvoted a collection about 2 months ago
EU20-Benchmarks
updated a collection about 2 months ago
Tokenisation-Bias
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 ByteSpan Tokenisers's profile picture co-evolve's profile picture Tiny Labs's profile picture