Reza Khan Mohammadi is a PhD candidate in Computer Science at Michigan State University, advised by Dr. Mohammad Ghassemi. His research develops confidence estimation methods for language, reasoning, and vision-language models, with the goal of determining when an AI system's output can be trusted and when it should be deferred to a clinician. In radiation oncology, he has worked with Henry Ford Health and Cedars-Sinai on automated toxicity extraction, CTCAE grading, and chart review, with findings published in the Red Journal and presented at AAPM, ASTRO, ICCR, and IEEE BHI. His work on language model confidence was nominated for an Outstanding Paper Award at EMNLP 2025, placing in the top 0.4% of more than 8,000 submissions.
Disclosures:
- Employment: none
- Compensation: none
- Ownership: none
- Leadership: none