Lewis and colleagues developed retrieval-augmented generation to link generative AI services to external resources, especially ones rich in the latest technical details.
The paper, with coauthors from the former Facebook AI Research (now Meta AI), University College London and New York University, called RAG “a general-purpose fine-tuning recipe” because it can be used by nearly any LLM to connect with practically any external resource.
Lewis and his team created retrieval-augmented generation to connect generative AI services with external assets, particularly those abundant with the most recent technical particulars.
The research paper, authored in collaboration with former Facebook AI Research (now known as Meta AI), University College London, and New York University, labeled RAG as "a versatile fine-tuning method" since it can be utilized by almost any LLM to link with virtually any external resource.
