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 about 10 hours ago

ActiveUltraFeedback/combined

jessicalamjh  updated a dataset 19 days ago

ActiveUltraFeedback/combined

jessicalamjh  updated a dataset 19 days ago

ActiveUltraFeedback/skywork

View all activity

Team members 3