Medical problem-solving demands expert knowledge and intricate reasoning. Recent studies of large language models (LLMs) attempt to ease this complexity by introducing external knowledge verification through retrieval-augmented generation or by training on reasoning datasets. However, these approaches suffer from drawbacks such as retrieval overhead and high annotation costs, and they heavily rely on substituted external assistants to reach limited performance in medical field. In this paper, we introduce MedReflect, a generalizable framework designed to inspire LLMs with a physician-like reflective thinking mode. MedReflect generates a single-pass reflection chain that includes initial hypothesis generation, self-questioning, self-answering and decision refinement. This self-verified and self-reflective nature releases large language model's latent capability in medical problem-solving without external retrieval or heavy annotation. We demonstrate that MedReflect enables cost-efficient medical dataset construction. With only a minimal subset of randomly sampled training examples and lightweight fine-tuning, this approach achieves notable absolute accuracy improvements across a series of medical benchmarks while significantly cutting annotation requirements. Our results provide evidence that LLMs can learn to solve specialized medical problems via self-reflection and self-improvement, reducing reliance on external supervision and extensive task-specific fine-tuning data.

翻译：医学问题求解需要专业知识和复杂推理能力。近期关于大语言模型的研究试图通过检索增强生成引入外部知识验证，或基于推理数据集进行训练来缓解这一复杂性。然而，这些方法存在检索开销高、标注成本大等缺陷，且过度依赖替代性外部助手，在医学领域仅能达到有限性能。本文提出MedReflect——一个通用化框架，旨在以类医师的反思思维模式激发大语言模型的潜能。该框架通过单次反思链生成实现初始假设构建、自我质疑、自我解答与决策优化。这种自我验证与自我反思的特性释放了大语言模型在医学问题求解中的潜在能力，无需外部检索或繁重标注。我们证明MedReflect能够实现经济高效的医学数据集构建：仅需随机采样的极小规模训练示例子集配合轻量微调，即可在一系列医学基准测试中取得显著绝对准确率提升，同时大幅降低标注需求。研究结果表明，大语言模型能够通过自我反思与自我改进学习解决专业医学问题，从而减少对外部监督和大量任务特定微调数据的依赖。