Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

​In this session, we are welcoming Zilong Wang from the University of California who co-authored the paper "Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting".

Check out the Paper here

​The research introduces SPECULATIVE RAG, a framework that leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM.

​See you there!