February 20, 2025
12:15 PM – 1:15 PM
Speaker:
Mami Hayashida, ITS-RCI, University of Kentucky and Vikram Gazula, CCS, University of Kentucky
Where:
327 McVey Hall
(Zoom link: https://uky.zoom.us/j/82467171189)
Title:
Introduction to Retrieval-Augmented Generation
Abstract:
Despite their impressive performance and versatility, LLMs are fundamentally limited by the data they were initially trained on. For researchers who wish to incorporate LLMs into their work, this often becomes a challenge as the available models trained on general knowledge fail to make reference to the domain knowledge. Similarly, LLMs do not keep up with the most up-to-date information as each LLM’s knowledge is “frozen”. RAG (Retrieval Augmented Generation) is a simple technique to overcome this gap by feeding additional knowledge to the LLM as part of workflow. When deployed effectively, the same LLMs will incorporate the added knowledge in generating responses as if they have quickly “ingested” the newly fed materials. In this session, we will cover the basic concepts of LLM + RAG, their use cases, and share simple code templates for experimentation. The prime target audience for this talk will be those who have limited (or no) knowledge of LLM and RAG, but would like to find out if and how these powerful tools can be incorporated into their research.