Bridging Academia and Industry with Generative AI: Unlocking the Power of Retrieval-Augmented Generation (RAG) for Education and Business
Document Type
Lecture
Publication Date
4-15-2025
Abstract
Advances in Large Language Models (LLMs) have intensified the need for academic programs and industry practitioners to collaborate on cutting-edge AI applications. Retrieval-Augmented Generation (RAG)—the integration of information retrieval mechanisms with LLMs—offers a powerful framework for producing accurate, context-rich outputs in real-world scenarios. In this talk, we present RAG’s theoretical underpinnings and demonstrate how it can be leveraged in both the classroom and the enterprise to meet evolving corporate demands, with real-world examples such as customer service in the insurance sector. We outline an end-to-end process for building a production-grade RAG system, discuss the challenges of scaling such solutions across industries, and highlight emerging research opportunities for students and professionals alike.
Relational Format
presentation
Recommended Citation
Miakonkana, Guy-vanie, "Bridging Academia and Industry with Generative AI: Unlocking the Power of Retrieval-Augmented Generation (RAG) for Education and Business" (2025). Probability & Statistics Seminar. 71.
https://egrove.olemiss.edu/math_statistics/71
