Beginners Guide to LLM/RAG Evaluation

Register here.

I frequently discuss various strategies for LLM/RAG evaluation, including real-time fine-tuning and measuring the quality of reconstructed taxonomies obtained with your RAG system, by comparing it to imported knowledge graphs from external input sources, or to the embedded taxonomy found in your crawled corpus. The following presentation explores the most important evaluation metrics, and how to implement and read them, with case studies.

RAG evaluation is a complex topic, similar to evaluating clustering techniques, because there is no "perfect" answer to compare to: RAG/LLM is typically an unsupervised machine learning problem. It is easier to evaluate RAG models that perform supervised tasks, such as classification or prediction based on training and validation sets.

Overview

Join us for an enlightening webinar on the innovative technology of Retrieval Augmented Generation (RAG) with Professor Tom Yeh from the University of Colorado Boulder. As AI continues to evolve, understanding technologies like RAG is crucial for anyone looking to stay ahead in the field. This webinar will introduce you to the basics of RAG, demonstrating how it enhances the capabilities of AI systems by integrating retrieval mechanisms into generative models.

You’ll learn:

• What RAG is and why it is a significant advancement in AI technology.
• How RAG improves the accuracy and reliability of AI-generated content.
• Practical applications of RAG in various industries including education, customer service, and more.
• Insights into the future developments and potential of RAG technology.

This hands-on workshop is for developers and AI professionals, featuring state-of-the-art technology, case studies, code-share, and live demos. Recording and GitHub material will be available to registrants who cannot attend the free 60-min session.

Register here.