A Reflection and Outlook on Clinical Adaption of Large Language Models
Track: Non-traditional track
Keywords: Large Language Model, Clinical Adaption
TL;DR: We analyzed the pathways through which existing clinical LLMs adapt to clinical domain, yielding intriguing observations and questions.
Abstract: The recent advancements in large language models have brought about a significant revolution in various aspects of natural language processing. The emergence of potent open-source LLMs has paved the way for domain-specific fine-tuning within the clinical field. A recent survey comprehensively summarized the latest applications in constructing clinical LLMs, highlighting both their challenges and applications. In this study, we aim to build upon this previous work and provide further in-depth analysis into existing clinical LLMs, with a focus on their domain adaption approaches. Our objective is to stimulate meaningful discussions among participants during the AAAI workshop. We believe that by delving into these aspects, we can contribute to a better understanding of the potential and limitations of clinical LLMs.
Presentation And Attendance Policy: I have read and agree with the symposium's policy on behalf of myself and my co-authors.
Ethics Board Approval: No, our research does not involve datasets that need IRB approval or its equivalent.
Data And Code Availability: Yes, we will make data and code available upon acceptance.
Primary Area: Clinical foundation models
Student First Author: Yes, the primary author of the manuscript is a student.
Submission Number: 19
Loading