Overview: In this workshop, we will continue our discussion of large language models by working through several examples of LLM application program interface (API) calls. In particular, we will be working with OpenAI’s LLM model GPT-4 to showcase its strengths as well as its pitfalls. Exercises will include the following two broad categories: 1. Using LLMs to generate synthetic data which can be analyzed or used for further studies (e.g., for verifying the validity of a given questionnaire) and 2. Using LLMs as synthetic data annotators (e.g., for qualitative analysis).

Prerequisites: Understanding and Using LLMs Responsibly: From Tools to Trust

Location: HYBRID. Online via Zoom, or in-person at Burnside Hall room 1104 (11th floor).
Instructor: Cesare Spinoso-Di Piano, PhD student in Computer Science, McGill University

IMPORTANT NOTE: for those attending the workshop online, you must log-into your McGill Zoom account. Otherwise, the link will not work. You can do so on the browser here: https://mcgill.zoom.us/ . For more information on McGill Zoom, please visit this website: https://www.mcgill.ca/tls/students/learning-resources/use-technology/learning-zoom