大语言模型可执行诊断推理
Large Language Models Perform Diagnostic Reasoning
AI总结：
该研究提出DR-CoT提示方法，将思维链提示扩展至医学自动诊断推理，仅用两个示例即可让通用大语言模型的诊断准确率较标准提示提升15%，域外场景下提升18%，验证了恰当提示可激发大模型的专家知识推理能力。
摘要：
我们探索将思维链（chain-of-thought, CoT）提示扩展至自动诊断任务的医学推理场景。受医生底层推理过程启发，我们提出诊断推理思维链（Diagnostic-Reasoning CoT, DR-CoT）。实证结果表明，仅用两个DR-CoT示例提示仅在通用文本语料上训练的大语言模型，诊断准确率较标准提示提升15%；此外，在域外场景下该差距达到显著的18%。我们的发现表明，大语言模型中的专家知识推理能力可通过恰当的提示被激发出来。
英文摘要：
We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper promptings.
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。
