Synthetic Data Generation using
Augmented Language Models (ALMs) pt. 2/3

Workshop | Dr Steve Bickley

Date:  31st July & 7 August  

Workshop:  10am-12pm

Location: QUT Gardens Point

Event Details

Speaker Details

Steve bickley

For Part 2/3 of Steve's workshop, we continue to explore the groundbreaking impact of Augmented Language Models (ALMs) such as OpenAI's ChatGPT and the innovative Assistants API on the landscape of research analytics. Harnessing the power of pre-trained models like GPT-3.5-turbo and GPT-4, along with impressive advancements from providers such as Google's Gemini and Anthropic's Claude series, ALMs are revolutionising empirical study designs. These technologies are driving forward augmented decision-making, particularly through synthetic data generation and silicon sampling. In this session, participants will engage in a hands-on exercise using SurveyLM, working in small groups to simulate and analyse complex agent behaviors. This exercise will offer a deep dive into real-world decision-making, leveraging research methods and tools from behavioural economics, and showcasing the profound capabilities and applications of ALMs in contemporary research.

Steve is a trained Behavioural Economist and Research Fellow at the ARC Training Centre for Behavioural Insights for Technology Adoption (BITA Centre) at QUT, dedicated to understanding how real-world factors shape human behaviour and decision-making. His unique blend of professional backgrounds in electrical engineering, project management, and behavioural economics has shaped his distinctive approach to problem-solving. Steve’s research delves into the complex systems literature and beyond, offering fresh perspectives and innovative approaches to behavioural economics and social AI, aiming to enrich these fields by making social science research more robust and effective. His innovative research culminated in his PhD thesis, "Bridging Complexity and Behavioural Economics: The Constrained Methods Matrix," which presents novel tools and insights for modeling and analyzing dynamic and complex societal systems, especially during unforeseen events like disease outbreaks and technological transformations.