Back to calls
ProgramMedicine & HealthRemote
Evaluating LLMs for summarizing clinical notes
Aurora Medical School
About this program
A one-year research program evaluating how large language models can safely summarize clinical documentation. Fellows collaborate across NLP, clinical medicine, and bioethics to build evaluation protocols, red-team model outputs, and publish reproducible benchmarks. The program is remote-friendly and includes regular clinical shadowing sessions to ground technical work in real workflows.
What's included
- Remote-first with optional clinical shadowing
- Co-authorship on published benchmarks
- Mentorship from clinicians and NLP researchers
- Structured research ethics training
Focus areas
NLPHealthcareEthics