Large Language Models for Clinical Data
Ahmed Alaa, Professor
Electrical Engineering and Computer Science
Check back for status
Large language models (LLMs) pre-trained on large corpora of text have
demonstrated incredible capabilities across with zero- or few-shot performance in new tasks that differ from their pre-training objectives. In this projects, we will study the zero-shot performance of LLMs for various clinical tasks using real-world clinical notes at the UCSF medical center.
Role: - Conducting experiments and maintaining a project codebase
- Regular presentation of progress in weekly lab meetings
- Assist in manuscript writing
- Workload expected to be > 12 hrs/week
- The student may engage in high-profile collaboration with industry research labs
Qualifications: - Strong programming skills
- Prior experience working with LLMs.
- Strong interest in pursuing graduate
Hours: 12 or more hours
Related website: https://www.nature.com/articles/s41746-024-01083-y
Related website: https://alaalab.berkeley.edu/