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

university

AI & ML interests

NLP, LLM Alignment, Preference Data generation, Active Learning

Recent Activity

davmel updated a collection 30 days ago

Preference Datasets

davmel updated a collection 30 days ago

Preference Datasets

davmel updated a collection 30 days ago

Preference Datasets

View all activity

davmel

updated a collection 30 days ago

Preference Datasets

40 items • Updated 30 days ago