Objective To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning. Methods We formulated 7 key clinical NLP tasks as text-to-text learning and solved them using one unified generative clinical LLM, GatorTronGPT, developed using GPT-3 architecture and trained with up to 20 billion parameters. We adopted soft prompts (ie, trainable vectors) with frozen LLM, where the LLM parameters were not updated (ie, frozen) and only the vectors of soft prompts were updated, known as prompt tuning. We added additional soft prompts as a prefix to the input layer, which were optimized during the prompt tuning. We evaluated the proposed method using 7 clinical NLP tasks and compared them with previous task-specific solutions based on Transformer models. Results and Conclusion The proposed approach achieved state-of-the-art performance for 5 out of 7 major clinical NLP tasks using one unified generative LLM. Our approach outperformed previous task-specific transformer models by ∼3% for concept extraction and 7% for relation extraction applied to social determinants of health, 3.4% for clinical concept normalization, 3.4%-10% for clinical abbreviation disambiguation, and 5.5%-9% for natural language inference. Our approach also outperformed a previously developed prompt-based machine reading comprehension (MRC) model, GatorTron-MRC, for clinical concept and relation extraction. The proposed approach can deliver the “one model for all” promise from training to deployment using a unified generative LLM.

中文翻译：

---

生成式大语言模型是通用文本分析引擎：文本到文本的学习就是您的全部需求

目的 通过即时调优，使用基于生成大语言模型 (LLM) 的统一文本到文本学习架构来解决主要的临床自然语言处理 (NLP) 任务。方法 我们将 7 个关键的临床 NLP 任务制定为文本到文本学习，并使用一种统一的生成临床 LLM GatorTronGPT 来解决这些任务，GatorTronGPT 使用 GPT-3 架构开发，并使用多达 200 亿个参数进行训练。我们采用了带有冻结LLM的软提示（即可训练向量），其中LLM参数不更新（即冻结），仅更新软提示的向量，称为提示调整。我们添加了额外的软提示作为输入层的前缀，并在提示调整过程中进行了优化。我们使用 7 个临床 NLP 任务评估了所提出的方法，并将它们与之前基于 Transformer 模型的特定任务解决方案进行了比较。结果和结论所提出的方法使用一个统一的生成法学硕士，在 7 个主要临床 NLP 任务中的 5 个中实现了最先进的性能。我们的方法在概念提取方面优于以前的特定任务变压器模型约 3％，在应用于健康社会决定因素的关系提取方面优于 7％，在临床概念标准化方面优于 3.4％，在临床缩写消歧方面优于 3.4％-10％，以及 5.5％- 9% 用于自然语言推理。我们的方法在临床概念和关系提取方面也优于之前开发的基于提示的机器阅读理解 (MRC) 模型 GatorTron-MRC。所提出的方法可以使用统一的生成法学硕士来实现从培训到部署的“所有人的单一模型”承诺。