Large Language Models and Financial Markets

This set of projects will explore the increasingly common use of Large Language Models (LLMs) in finance and accounting research. Assistance is needed to clean various text-based datasets. We will also need help with analyzing the data using LLMs on the Yale SOM computing cluster.

Requisite Skills and Qualifications:

Coursework in econometrics or statistics and advanced coding knowledge (Python) is required. Specifically, familiarity with the following libraries is required: pandas, numpy, and statsmodels. The ideal candidate will also have experience coding with LLMs and RAG or, at a minimum, experience with other NLP techniques.