诊断推理提示揭示了大型语言模型在医学中的可解释性潜力
Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine
AI总结：
本文提出新型诊断推理提示，证明GPT4可在保持诊断准确性的同时模拟临床医生推理并给出可解释依据，从而提升医学LLM的可信度与安全应用潜力。
摘要：
在医学中使用大型语言模型（LLM）的主要障碍之一，是人们认为它们采用不可解释的方法作出临床决策，而这些方法在本质上不同于临床医生的认知过程。在本文中，我们开发了新颖的诊断推理提示，用以研究LLM是否能够执行临床推理，从而准确形成诊断。我们发现，可以通过提示使GPT4模拟临床医生常见的临床推理过程，同时不牺牲诊断准确性。这一点具有重要意义，因为能够运用临床推理提供可解释理由的LLM，为医生评估LLM是否可被信任用于患者护理提供了一种手段。新颖的提示方法有可能揭开LLM的黑箱，使它们距离在医学中安全、有效地使用更近一步。
英文摘要：
One of the major barriers to using large language models (LLMs) in medicine is the perception they use uninterpretable methods to make clinical decisions that are inherently different from the cognitive processes of clinicians. In this manuscript we develop novel diagnostic reasoning prompts to study whether LLMs can perform clinical reasoning to accurately form a diagnosis. We find that GPT4 can be prompted to mimic the common clinical reasoning processes of clinicians without sacrificing diagnostic accuracy. This is significant because an LLM that can use clinical reasoning to provide an interpretable rationale offers physicians a means to evaluate whether LLMs can be trusted for patient care. Novel prompting methods have the potential to expose the black box of LLMs, bringing them one step closer to safe and effective use in medicine.
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。
