Integrating Large Language Models (LLMs) into the Data Science Workflow Speaker: Rohan Alexander

The SCV section invites you to the webinar, Integrating Large Language Models (LLMs) into the Data Science Workflow with Rohan Alexander.

This talk will begin with an overview of Large Language Models, such as OpenAI's GPT-4. He will then discuss one way that LLMs can be integrated into a data science workflow: to generate data validation tests. He will focus on the effect of different settings on the decency and consistency of the LLM responses. LLM-generated responses were found to compare well against a gold standard suite, created by an experienced data scientist knowledgeable about the dataset in question.

Bio: Rohan Alexander is an Assistant Professor at the University of Toronto, jointly appointed in the Faculty of Information and the Department of Statistical Sciences. He's also the Assistant Director of Canadian Statistical Sciences (CANSSI) Ontario and a Senior Fellow at Massey College. His research investigates how we can develop workflows that improve the trustworthiness of data science, and he is particularly interested in the role of testing in data science. He holds a PhD in Economics from the Australian National University, where he focused on Australian economic history.