Researcher & PM (LLM) for a joint project with a research institute, Oct. 2024 ~

In a joint project with a research institute, we conducted a Proof of Concept (PoC) to explore the application of Large Language Models (LLMs) to healthcare-related big data.

A central theme in this field is the prediction of future health conditions, but its practical application faces several hurdles. Data confidentiality is a significant barrier, which highlights the value of using Local and Domain-Specific LLMs. To this end, we developed a prototype that integrates multiple estimation methods to perform causal inference between data points.

I served in a dual capacity as both a Researcher and a Project Manager (PM).

As a researcher, my primary challenge was problem formulation. Given the project’s complexity, I had to address several critical issues, including selecting relevant data from a vast dataset, establishing evaluation criteria, and defining the ground truth appropriately for each inference method.

As a PM, I was responsible for assigning tasks to a team of AI engineers and managing their progress.

Ultimately, the PoC yielded valuable insights into both medical and mathematical research questions. These findings will serve as the foundation for our next joint research initiative.