arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.10822cs.CL
收藏

大型语言模型能否抽象医学编码语言?

Can Large Language Models abstract Medical Coded Language?

University of California, Los Angeles(加州大学洛杉矶分校)

Simon A. Lee, Timothy Lindsey

AI总结:

本研究评估GPT、LLaMA-2和Meditron等大型语言模型对ICD-10等医学编码本体的理解与名称生成能力,发现其在编码语言上表现不佳,并提出改进推理的方法。

摘要:

大型语言模型(LLMs)已成为一个关键的研究领域,在医疗保健等领域可能做出有益贡献,例如简化自动计费和决策支持。然而,频繁使用像ICD-10这样的专用编码语言——这些编码会定期更新并偏离自然语言格式——给LLMs在创建准确且有意义的潜在表示方面带来了潜在挑战。这引发了医疗保健专业人员对潜在不准确或“幻觉”的担忧,这些不准确或幻觉可能直接影响患者。因此,本研究评估大型语言模型(LLMs)是否了解医学代码本体,并能否根据这些代码准确生成名称。我们评估了通用生成模型和生物医学专用生成模型(如GPT、LLaMA-2和Meditron)的能力与局限性,重点关注它们在领域特定术语方面的熟练程度。虽然结果表明LLMs在处理编码语言方面存在困难,但我们提供了关于如何调整这些模型以更有效地进行推理的见解。

英文摘要:

Large Language Models (LLMs) have become a pivotal research area, potentially making beneficial contributions in fields like healthcare where they can streamline automated billing and decision support. However, the frequent use of specialized coded languages like ICD-10, which are regularly updated and deviate from natural language formats, presents potential challenges for LLMs in creating accurate and meaningful latent representations. This raises concerns among healthcare professionals about potential inaccuracies or ``hallucinations" that could result in the direct impact of a patient. Therefore, this study evaluates whether large language models (LLMs) are aware of medical code ontologies and can accurately generate names from these codes. We assess the capabilities and limitations of both general and biomedical-specific generative models, such as GPT, LLaMA-2, and Meditron, focusing on their proficiency with domain-specific terminologies. While the results indicate that LLMs struggle with coded language, we offer insights on how to adapt these models to reason more effectively.

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。

↑