Abstract: 

In the realm of advanced computational linguistics, the efficacy of Large Language Models (LLMs) is intrinsically tied to their contextual precision. In this session presented by Jake from Cloudera (not State Farm), we'll navigate the complexities of ensuring LLMs yield contextually accurate results, a necessity in today's intricate data environments. Crucially, attendees will be treated to a live demonstration showcasing the utilization of RAG (Retrieval-Augmented Generation) and PEFT (Parameter Efficient Fine-Tuning) techniques, two of the leading approaches for this task that underpin the success of Cloudera's Applied ML Prototypes (AMPs).

Session Objective: Equip attendees with an understanding of LLM contextual enhancement techniques, underscored by practical demonstrations of RAG and Parameter Efficient Fine-Tuning.

Learning Outcomes:

- Comprehend the pivotal role of contextual accuracy in LLMs.
- Witness hands-on techniques for optimizing LLMs using RAG and Parameter Efficient Fine-Tuning.
- Grasp challenges and solutions in the LLM training process
- Acquire actionable strategies to enhance the contextual accuracy of LLMs in diverse applications.
- Understand how Cloudera’s Applied ML Prototypes help reduce time-to-value for building LLM Applications

Dive into this session to transform your LLM applications from merely knowledgeable to sharply context-aware, fortified by real-world techniques.

Session Outline:

- Comprehend the pivotal role of contextual accuracy in LLMs.
- Witness hands-on techniques for optimizing LLMs using RAG and Parameter Efficient Fine-Tuning.
- Grasp challenges and solutions in the LLM training process
- Acquire actionable strategies to enhance the contextual accuracy of LLMs in diverse applications.
- Understand how Cloudera’s Applied ML Prototypes help reduce time-to-value for building LLM Applications

Bio: 

Jake currently holds the position of Principal Technical Evangelist at Cloudera, where he promotes the strengths of Cloudera’s Lakehouse for delivering trusted AI. His tenure at Cloudera began as a Senior Product Marketing Manager for Cloudera Machine Learning (CML).

Before Cloudera, Jake developed his ML expertise at ExxonMobil, starting as a Data Scientist and later transitioning to a Data Science and Analytics Solution Architect role. He also contributed significantly at FarmersEdge, taking on responsibilities as a Senior Data Scientist and subsequently as a Data Science Manager.

Jake earned both his bachelor’s and master’s degrees from Brigham Young University in Information Systems Management with an emphasis in Statistics.

Outside of work, Jake is passionate about outdoor activities. He enjoys skiing, golfing, rafting, and hiking. However, spending time with his family amidst the mountains remains his most rewarding pastime.