Abstract
Online medical consultations generate large volumes of conversational health data that often embed protected health information, requiring robust methods to classify data categories and assign risk levels in line with policies and practice. However, existing approaches lack unified standards and reliable automated methods to fulfill sensitivity classification for such conversational health data. This study presents a large language model-based extraction pipeline, SALP-CG, for classifying and grading privacy risks in online conversational health data. We concluded health-data classification and grading rules in accordance with GB/T 39725-2020. Combining few-shot guidance, JSON Schema constrained decoding, and deterministic high-risk rules, the backend-agnostic extraction pipeline achieves strong category compliance and reliable sensitivity across diverse LLMs. On the MedDialog-CN benchmark, models yields robust entity counts, high schema compliance, and accurate sensitivity grading, while the strongest model attains micro-F1=0.900 for maximum-level prediction. The category landscape stratified by sensitivity shows that Level 2-3 items dominate, enabling re-identification when combined; Level 4-5 items are less frequent but carry outsize harm. SALP-CG reliably helps classify categories and grading sensitivity in online conversational health data across LLMs, offering a practical method for health data governance. Code is available at this https URL.
Abstract (translated)
在线医疗咨询生成了大量的对话健康数据，这些数据中往往包含受保护的健康信息，需要有强大的方法来分类数据类别并根据政策和实践为其分配风险级别。然而，现有的方法缺乏统一的标准和可靠的自动化手段来进行此类对话健康数据的敏感性分类。本研究提出了一种基于大型语言模型的提取管道SALP-CG，用于在线对话健康数据中隐私风险的分类与分级。我们依照GB/T 39725-2020标准制定了健康数据分类和分级规则。结合少量样本指导、JSON Schema约束解码及确定性高风险规则，该后台无关提取管道在不同大型语言模型上实现了强大的类别合规性和可靠的敏感度。 在MedDialog-CN基准测试中，模型显示了稳健的实体计数、高水平的模式符合以及准确的敏感级别分级。最强力的模型达到了最大级预测的微平均F1值为0.900。根据敏感性对类别的分布情况进行细分后可以发现，2-3级别的条目占主导地位，并且在结合使用时能够实现再识别；4-5级别的条目较少但危害巨大。 SALP-CG可靠地帮助跨大型语言模型在线对话健康数据分类和分级，为健康管理提供了一种实用的方法。代码可以在提供的链接中获取。
URL
https://arxiv.org/abs/2601.09717
