Open Unlearning

AI & ML interests

Large Language Model unlearning

Recent Activity

pratyushmaini  authored a paper 9 days ago

Follow the Gradient: Tracing Safety Degradation Back to Training Data

pratyushmaini  authored a paper 9 days ago

Natively Unlearnable Large Language Models

pratyushmaini  authored a paper 9 days ago

LLM Dataset Inference: Did you train on my dataset?

View all activity

Team members 5