My project investigates how large language models (LLMs) act when deployed in financial markets by integrating perspectives from artificial intelligence, finance, and social sciences. We study how the learned biases of LLMs affect the dynamics of the systems they are deployed in. For this project, the learned biases of LLMs we are looking at are economic biases like risk aversion, and the system of LLMs is a simulated financial market. We are investigating how different LLMs with different levels of behavioral bias will affect the efficiency of financial markets.

I am participating in Super UROP to connect my main interest areas AI, mathematics and finance through high-level research. This is a great opportunity for me to do work in the intersection of my majors Business (15-2) and AI (6-4), while learning more about financial markets, and how to work with LLMs.