A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Aniruddha Roy, Pretam Ray, Abhilash Nandy, et al.
REFINE-AF uses reinforcement learning from automated feedback to generate high-quality instruction datasets from a small seed set, outperforming Self-Instruct.
Unknown
Alpaca fine-tunes LLaMA 7B on instruction-following demonstrations generated via self-instruct from text-davinci-003.
Unknown
Self-Instruct bootstraps instruction-following in language models using their own generations, reducing annotation needs.