不用微调大模型，用提示工程就能高效提取医疗医嘱。
Assessing Large Language Models for Structured Medical Order Extraction
- 用指令微调的LLaMA-4模型，仅靠一个示例进行少样本推理。
- 平均F1达37.76，原因和来源识别准确率显著提升。
- 适合需要快速部署的临床NLP场景，无需领域数据训练。
医疗医嘱提取对结构化临床信息、支持决策及实现文档生成与流程自动化至关重要。医嘱可能嵌入电子病历、出院记录和多轮医患对话中，涵盖药物、检验、影像和随访等类别。MEDIQA-OE 2025共享任务聚焦从长篇对话转录文本中提取结构化医嘱，需识别医嘱类型、描述、原因和来源。我们提交的MasonNLP方案在17支队伍共105个提交中位列第5。方法采用未进行领域微调的通用指令调优版LLaMA-4 17B模型，仅通过单个上下文示例引导。该少样本配置取得平均F1分数37.76，尤其在原因与来源识别上表现优异。结果表明，结合有效提示工程，通用非领域大模型可成为特定临床自然语言处理任务的强而可扩展基线。
原文摘要 · Abstract (English)
Medical order extraction is essential for structuring actionable clinical information, supporting decision-making, and enabling downstream applications such as documentation and workflow automation. Orders may be embedded in diverse sources, including electronic health records, discharge summaries, and multi-turn doctor-patient dialogues, and can span categories such as medications, laboratory tests, imaging studies, and follow-up actions. The MEDIQA-OE 2025 shared task focuses on extracting structured medical orders from extended conversational transcripts, requiring the identification of order type, description, reason, and provenance. We present the MasonNLP submission, which ranked 5th among 17 participating teams with 105 total submissions. Our approach uses a general-purpose, instruction-tuned LLaMA-4 17B model without domain-specific fine-tuning, guided by a single in-context example. This few-shot configuration achieved an average F1 score of 37.76, with notable improvements in reason and provenance accuracy. These results demonstrate that large, non-domain-specific LLMs, when paired with effective prompt engineering, can serve as strong, scalable baselines for specialized clinical NLP tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。