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

AI & ML interests

NLP, LLM Alignment, Preference Data generation, Active Learning

Recent Activity

jessicalamjh  published a dataset 8 days ago

ActiveUltraFeedback/combined

jessicalamjh  updated a dataset 27 days ago

ActiveUltraFeedback/combined

jessicalamjh  updated a dataset 27 days ago

ActiveUltraFeedback/skywork

View all activity

Team members 3