Retrieval-Augmented Generation (RAG)

Introduction

• Speaker: Marina Danilevsky, Senior Research Scientist at IBM Research
• Topic: Enhancing accuracy and currency of Large Language Models (LLMs) using Retrieval-Augmented Generation (RAG)

Basic Concepts

Generation in LLMs

• LLMs: Generate text in response to user queries (prompts).
• Challenges:
  • No source citation for generated information.
  • Information can be outdated.

Illustration with an Anecdote

• Example Question: