RAFT: Adapting Language Models To RAG

In the rapidly advancing field of AI, Large Language Models (LLMs) are breaking new ground. Once primarily used for providing information within dialogue systems, these models are now stepping into a realm where they can actively engage with tools and execute actions on real-world applications and services with little to no human intervention. In this talk, Tianjun Zhang presents Gorilla (tool usage) and RAFT (RAG and document understanding), a series of fine-tuned models developed for building LLM agents.