ActiveUltraFeedback: Sample-Efficient RLHF Preference data generation using Active Learning

AI & ML interests

NLP, LLM Alignment, Preference Data generation, Active Learning

Recent Activity

jessicalamjh  authored a paper 11 days ago

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

davmel  authored a paper 12 days ago

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

davmel  updated a Space 13 days ago

ActiveUltraFeedback/README

View all activity

Team members 3