检索增强与知识 grounded 语言模型用于可靠的临床医学
Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine
AI总结：
提出Re$^3$Writer方法，结合检索增强生成与知识推理，使语言模型生成可靠的临床文本，在出院指导任务上显著提升五个模型的性能。
摘要：
语言模型（LMs），包括大型语言模型（如 ChatGPT），有潜力协助临床医生生成各种临床笔记。然而，语言模型容易产生“幻觉”，即生成的内容与事实和知识不符。在本文中，我们提出了 Re$^3$Writer 方法，结合检索增强生成和知识 grounded 推理，使语言模型能够生成可靠的临床文本。我们展示了该方法在生成患者出院指导方面的有效性。这要求语言模型不仅要理解患者的长期临床文档，即住院期间的健康记录，还要生成在出院时提供给护理人员和患者的关键指导信息。所提出的 Re$^3$Writer 模仿医生的工作模式，首先从医生先前编写的指导中检索相关工作经历，然后推理相关的医学知识。最后，它提炼检索到的工作经历和推理出的医学知识以提取有用信息，用于为未见过的患者生成出院指导。我们的实验表明，使用我们的方法，五个代表性语言模型的性能在所有指标上均显著提升。同时，我们展示了人工评估的结果，以衡量在流畅性、可靠性和全面性方面的有效性。
英文摘要：
Language models (LMs), including large language models (such as ChatGPT), have the potential to assist clinicians in generating various clinical notes. However, LMs are prone to produce ``hallucinations'', i.e., generated content that is not aligned with facts and knowledge. In this paper, we propose the Re$^3$Writer method with retrieval-augmented generation and knowledge-grounded reasoning to enable LMs to generate faithful clinical texts. We demonstrate the effectiveness of our method in generating patient discharge instructions. It requires the LMs not to only understand the patients' long clinical documents, i.e., the health records during hospitalization, but also to generate critical instructional information provided both to carers and to the patient at the time of discharge. The proposed Re$^3$Writer imitates the working patterns of physicians to first \textbf{re}trieve related working experience from historical instructions written by physicians, then \textbf{re}ason related medical knowledge. Finally, it \textbf{re}fines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the discharge instructions for previously-unseen patients. Our experiments show that, using our method, the performance of five representative LMs can be substantially boosted across all metrics. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of fluency, faithfulness, and comprehensiveness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
