O1复现之旅——第3部分：面向医学推理的推理时缩放
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning
AI总结：
本研究在O1复现前期工作基础上，探索大语言模型推理时缩放在医学推理中的作用，通过多基准实验验证了其性能提升效果及与任务复杂度的关联，证实了其与journey learning协同提升临床推理能力的潜力。
摘要：
在我们此前关于O1复现的研究（第1部分：Journey Learning[Qin等人，2024]；第2部分：Distillation[Huang等人，2024]）基础上，本工作探索了大语言模型（LLM）的推理时缩放在医学推理任务中的潜力，任务范围涵盖诊断决策到治疗规划。通过在不同复杂度的医学基准（MedQA、Medbullets和JAMA Clinical Challenges）上开展大量实验，本研究得出了若干关键结论：（1）增加推理时长确实能提升性能。仅使用500个样本的小型训练集，我们的模型就实现了6%-11%的显著性能提升。（2）任务复杂度与所需推理链长度直接相关，证实了复杂问题需要更长思维过程的必要性。（3）我们的模型生成的鉴别诊断遵循假设-演绎法原则，先列出可能解释患者症状的潜在病症清单，再通过评估证据系统地缩小这些可能性范围。这些发现表明，推理时缩放与journey learning之间的协同作用在提升大语言模型的实际临床推理能力方面具有广阔前景。
英文摘要：
Building upon our previous investigations of O1 replication (Part 1: Journey Learning [Qin et al., 2024] and Part 2: Distillation [Huang et al., 2024]), this work explores the potential of inference-time scaling in large language models (LLMs) for medical reasoning tasks, ranging from diagnostic decision-making to treatment planning. Through extensive experiments on medical benchmarks of varying complexity (MedQA, Medbullets, and JAMA Clinical Challenges), our investigation reveals several key insights: (1) Increasing inference time does lead to improved performance. With a modest training set of 500 samples, our model yields substantial performance improvements of 6%-11%. (2) Task complexity directly correlates with the required length of reasoning chains, confirming the necessity of extended thought processes for challenging problems. (3) The differential diagnoses generated by our model adhere to the principles of the hypothetico-deductive method, producing a list of potential conditions that may explain a patient's symptoms and systematically narrowing these possibilities by evaluating the evidence. These findings demonstrate the promising synergy between inference-time scaling and journey learning in advancing LLMs' real-world clinical reasoning capabilities.
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。
