UROP Project

Improving AI reliability for healthcare applications

AI, LLM, healthcare

Research Mentor: Guang Wang,
Department, College, Affiliation: Computer Science, Arts and Sciences
Contact Email: guang.wang@fsu.edu
Research Assistant Supervisor (if different from mentor):
Research Assistant Supervisor Email:
Faculty Collaborators:
Faculty Collaborators Email:

Looking for Research Assistants: Yes
Number of Research Assistants: 1
Relevant Majors: Open to all majors.
Project Location: On FSU Main Campus
Research Assistant Transportation Required:
Remote or In-person: Partially Remote
Approximate Weekly Hours: 10, Flexible schedule (Combination of business and outside of business. TBD between student and research mentor.)
Roundtable Times and Zoom Link:
Not participating in the roundtable

Project Description

This project aims to develop reliable artificial intelligence (AI) methods for healthcare applications, with a focus on improving the trustworthiness of AI-assisted clinical decision-making. The research will address key reliability challenges, including uncertainty estimation and calibration, hallucinations and factual errors, and robustness and generalization across diverse patient populations, clinical settings, and data distributions. By developing methods that can better quantify confidence, identify unreliable predictions or generated outputs, and maintain stable performance under changing conditions, the project seeks to enable safer and more dependable use of AI in healthcare. The ultimate goal is to provide trustworthy AI tools that can effectively support healthcare professionals in making informed clinical decisions.

Research Tasks: Data collection, data analysis, and conduct experiments with LLMs.

Skills that research assistant(s) may need: Has healthcare background (recommended).