Scholarlink

<p>To enhance the reasoning stability of small-parameter medical large language models in internal medicine question-answering tasks, this paper proposes a training methodology based on explicit chain-of-thought (CoT) modeling and hybrid supervised fine-tuning (SFT). First, a hierarchical dataset comprising general internal medicine instructions and explicit CoT data was constructed. On this basis, a two-stage hybrid SFT process was implemented, incorporating direct preference optimization to align the model with clinical preferences. Experimental results demonstrate that the proposed method improves the accuracy on Chinese medical benchmarks while reducing the proportion of redundant reasoning, effectively enhancing the logical rigor of complex clinical inquiries. Furthermore, these findings validate the potential of this approach for deploying low-cost, highly reliable, and localized auxiliary diagnostic systems in privacy-sensitive and compute-constrained clinical scenarios.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid Supervised Fine-Tuning Method for Medical Language Models via Explicit Reasoning Modeling

  • 期刊论文

  • 发表日期：

    2026年5月28日

查看全文
  • Xu Wang,
  • Wei Tao,
  • Zhuojiang Nan,
  • Song Wan

摘要

To enhance the reasoning stability of small-parameter medical large language models in internal medicine question-answering tasks, this paper proposes a training methodology based on explicit chain-of-thought (CoT) modeling and hybrid supervised fine-tuning (SFT). First, a hierarchical dataset comprising general internal medicine instructions and explicit CoT data was constructed. On this basis, a two-stage hybrid SFT process was implemented, incorporating direct preference optimization to align the model with clinical preferences. Experimental results demonstrate that the proposed method improves the accuracy on Chinese medical benchmarks while reducing the proportion of redundant reasoning, effectively enhancing the logical rigor of complex clinical inquiries. Furthermore, these findings validate the potential of this approach for deploying low-cost, highly reliable, and localized auxiliary diagnostic systems in privacy-sensitive and compute-constrained clinical scenarios.