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
new activity
28 days ago
cmeister/multilingual-tok-corpus:Create README.md
upvoted
a
collection
about 2 months ago
EU20-Benchmarks
updated
a collection
about 2 months ago
Tokenisation-Bias