大型语言模型是临床推理器：采用提示生成理由的推理感知诊断框架
Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对临床理由标注昂贵、诊断推理研究不足的问题，提出推理感知诊断框架，利用提示生成 Clinical CoT 理由并学习推理，实验验证 LLM/LM 的临床推理能力。
AI中文摘要：
近年来，得益于大型语言模型（LLM），机器推理取得了巨大进展。然而在临床领域，由于需要临床医生参与的理由标注成本高昂，大多数由 NLP 驱动的项目主要关注临床分类或阅读理解，对疾病诊断中的临床推理探索不足。在本研究中，我们提出一种“推理感知”诊断框架，通过基于提示的学习以省时、省力的方式使诊断过程合理化，并学习基于提示生成的理由进行推理。具体而言，我们处理疾病诊断中的临床推理：LLM 生成诊断理由，针对所呈现的患者数据及其通向诊断的推理路径提供洞见，即 Clinical Chain-of-Thought（Clinical CoT，临床思维链）。我们在多种设置下对理由生成和疾病诊断开展大量实验与分析，实证证明了 LLM/LM 的临床推理能力。我们还进一步提出一套新颖的标准，用于评估机器生成理由在真实世界临床场景中的潜力，从而促进并惠及该领域未来研究。
英文摘要：
Machine reasoning has made great progress in recent years owing to large language models (LLMs). In the clinical domain, however, most NLP-driven projects mainly focus on clinical classification or reading comprehension, and under-explore clinical reasoning for disease diagnosis due to the expensive rationale annotation with clinicians. In this work, we present a "reasoning-aware" diagnosis framework that rationalizes the diagnostic process via prompt-based learning in a time- and labor-efficient manner, and learns to reason over the prompt-generated rationales. Specifically, we address the clinical reasoning for disease diagnosis, where the LLM generates diagnostic rationales providing its insight on presented patient data and the reasoning path towards the diagnosis, namely Clinical Chain-of-Thought (Clinical CoT). We empirically demonstrate LLMs/LMs' ability of clinical reasoning via extensive experiments and analyses on both rationale generation and disease diagnosis in various settings. We further propose a novel set of criteria for evaluating machine-generated rationales' potential for real-world clinical settings, facilitating and benefiting future research in this area.
