There is enormous enthusiasm and concerns in using large language models
(LLMs) in healthcare, yet current assumptions are all based on general-purpose
LLMs such as ChatGPT. This study develops a clinical generative LLM,
GatorTronGPT, using 277 billion words of mixed clinical and English text with a
GPT-3 architecture of 20 billion parameters. GatorTronGPT improves biomedical
natural language processing for medical research. Synthetic NLP models trained
using GatorTronGPT generated text outperform NLP models trained using
real-world clinical text. Physicians Turing test using 1 (worst) to 9 (best)
scale shows that there is no significant difference in linguistic readability
(p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical
relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that
physicians cannot differentiate them (p < 0.001). This study provides insights
on the opportunities and challenges of LLMs for medical research and
healthcare.

本文使用 2770 亿行混合临床和英文文本的 GPT-3 架构，开发了一种名为 GatorTronGPT 的临床生成 LLM，以提高医学研究的生物医学自然语言处理。通过使用 GatorTronGPT 训练的合成自然语言处理模型的生成文本，性能优于使用现实临床文本训练的模型。在医生的图灵测试中，医生不能区分 GatorTronGPT 所生成的文本和人类所生成的文本。该研究为 LLMs 在医学研究和医疗保健中的机遇和挑战提供了深入的见解。