基于标签的示例选择在少样本学习中生成医疗事件因果因素和预防措施
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
AI总结：
本文提出基于标签的少样本学习方法，利用日本医疗事件数据集，通过对比随机采样、相似度选择和标签方法，验证标签选择能提高生成精度和稳定性。
摘要：
在高风险领域如医疗健康中，大型语言模型（LLMs）的可靠性至关重要，特别是在从事件报告中生成临床见解时。本研究提出了一种基于标签的少样本示例选择方法，用于提示LLMs生成医疗事件的背景/因果因素和预防措施。我们使用日本医疗事件数据集（JMID），该数据集包含3,884个真实世界医疗事故和近失事件报告。这些报告被赋予了广泛的标签，包括描述性信息（如“药物”、“输血治疗”）。我们比较了三种少样本示例选择策略——随机采样、基于余弦相似度的选择和我们提出的方法——使用GPT-4o和LLaMA 3.3。结果表明，基于标签的方法在精度和生成行为的稳定性方面最高，而基于相似度的选择常导致意外输出和安全过滤器激活。这些发现表明，基于人类可解释的数据集标签选择示例可以提高临床LLM应用中的生成精度和稳定性。
英文摘要：
In high-stakes domains such as healthcare, the reliability of Large Language Models (LLMs) is critical, particularly when generating clinical insights from incident reports. This study proposes a tag-based few-shot example selection method for prompting LLMs to generate background/causal factors and preventive measures from details of the medical incidents. For our experiments, we use the Japanese Medical Incident Dataset (JMID), a structured dataset of 3,884 real-world medical accident and near-miss reports. These reports are variably annotated with a wide range of tags--some include descriptive information (e.g., "medications," "blood transfusion therapy"). We compare three few-shot example selection strategies--random sampling, cosine similarity-based selection, and our proposed tag-based method--using GPT-4o and LLaMA 3.3. Results show that the tag-based approach achieves the highest precision and most stable generation behavior, while similarity-based selection often leads to unintended outputs and safety filter activation. These findings suggest that selecting examples based on human-interpretable dataset tags can improve generation precision and stability in clinical LLM applications.
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。
