Models pretrained on various obfuscated versions of the same dataset to analyse how the obfuscation affects downstream performance.
Daniel Gallagher
DanielGallagherIRE
AI & ML interests
NLP at the Institute for Applied Informatics in Leipzig, Germany.
Recent Activity
published a dataset about 1 hour ago
DanielGallagherIRE/fwedu20b-E1-mutual-information updated a collection about 7 hours ago
Obfuscated ModernBERT updated a dataset 2 days ago
DanielGallagherIRE/fwedu20b-E1-scramble-BoW