Generative Question Answering
Patrick discusses the evolution of question answering systems, highlighting the transition from extractive methods to generative models. He shares insights on the integration of retrieval systems with neural models and explores the significance of in-context learning through experiments like the llama probe and alpaca. The conversation emphasizes the collaborative efforts that led to advancements in retrieval augmented generation techniques.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Patrick Lewis (Cohere) - Retrieval Augmented Generation
Related Questions