Generative Models Unleashed
Patrick discusses the evolution of retrieval augmented generation (RAG) and its roots in collaborative ideas among researchers. He emphasizes the empirical focus of their initial work, which aimed to enhance open domain question answering through generative models. The conversation highlights how the term RAG has expanded over time, becoming a catch-all for various approaches to integrating knowledge with language models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Patrick Lewis (Cohere) - Retrieval Augmented Generation
Related Questions
How do you use Retrieval-Augmented Generation (RAG) with a Language Model as discussed in the episode Patrick Lewis on Retrieval-Augmented Generation - Weaviate Podcast #76! and the clip Atlas Paper Insights?
Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data as discussed in the episode Patrick Lewis on Retrieval-Augmented Generation - Weaviate Podcast #76! and the clip Unsupervised Retrieval Models?