Gen AI Meetup #3

Talk 1: Optimising Data for LLMs: Strategies for effective RAG
Jordan Moshcovitis

Data preparation not only enhances the accuracy of Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) but is also effective in improving their output relevance. This presentation will examine strategies that boost the semantic integrity and efficiency of data retrieval systems supporting LLMs. We will explore the progression from traditional RAG techniques to advanced methods such as propositional and semantic chunking, emphasising the role of thorough data preprocessing. Additionally, the discussion will include the deployment o tools that facilitate semantic enhancements and the deserialization of complex document structures, which collectively refine the efficacy of RAG applications.

About the presenter: Jordan is an engineer and researcher with a formal background in physics and mathematics. His current focus is on developing application-layer services for large language models, specifically information retrieval techniques like retrieval augmented generation (RAG) and LLM agents. Jordan has demonstrated his expertise through a variety of projects, from constructing bionic eye prototypes to deploying advanced ML models for uncertainty quantification in physical systems. His career is marked by a passion for applying quantitative methods in diverse settings, tackling complex problems and an passion for innovation in technology. With understanding of both the theoretical underpinnings and practical applications of LLMs, Jordan works to extend the capabilities of LLMs to transform complex data into actionable insights and bridge the gap between theoretical research and practical, scalable applications in AI.

Talk 2: Innovating for GenAI products and services
Scott Barnett

Australia has a great opportunity to capitalise on generative AI! However, scepticism is building on whether the investment in generative AI is worth it - in many cases the value has yet to materialise. At the same time, new capabilities and services are announced seemingly daily. This talk will highlight the challenges of why this is the case and what we can do about it - the key is where and how we innovate for generative AI.

About the presenter: Dr. Scott Barnett is Deputy Head, Translational Research and Commercialisation at the Applied Artificial Intelligence Institute (A2I2) at Deakin University. Dr Barnett leads the generative AI projects at A2I2 where he helps organisations integrate intelligent agents into business workflows. Dr Barnett received his PhD from Swinburne University in Software Architecture and has over 8 years’ experience working in technical roles. He started the GenAI Network to help Australia adapt and adopt to generative AI.