在笔记本电脑上实现隐私保护的医疗问答，性能接近云端大模型。
sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook
- 仅用本地硬件和无云架构，部署轻量级模型解决电子病历问答。
- 在四个子任务中两项表现优于平均，小模型经调优可逼近大模型效果。
- 适合关注医疗数据隐私、资源受限场景的临床研究与应用开发者。
基于电子健康记录（EHR）的临床问答能更高效地帮助医护人员和患者获取医疗信息。然而，许多现有方法依赖大型云端模型，因隐私限制和计算需求难以在临床环境中部署。本文研究在单台笔记本电脑上实现完全本地化的、基于EHR的问答系统所能达到的极限。我们参与了ArchEHR-QA 2026共享任务全部四个子任务，评估多种可在消费级硬件运行的方法。所有实验均在无外部API或云基础设施的环境下进行。结果表明，此类系统可在共享任务排行榜上取得具有竞争力的表现：我们的提交在两个子任务中优于平均水平；同时发现，经过合理配置的小型模型可接近大型系统性能。这表明，利用当前模型与通用硬件，实现完全本地化且隐私保护的EHR问答是可行的。代码已公开于 https://github.com/ibrahimey/ArchEHR-QA-2026。
原文摘要 · Abstract (English)
Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical environments due to privacy constraints and computational requirements. In this work, we investigate how far grounded EHR question answering can be pushed when restricted to a single notebook. We participate in all four subtasks of the ArchEHR-QA 2026 shared task and evaluate several approaches designed to run on commodity hardware. All experiments are conducted locally without external APIs or cloud infrastructure. Our results show that such systems can achieve competitive performance on the shared task leaderboards. In particular, our submissions perform above average in two subtasks, and we observe that smaller models can approach the performance of much larger systems when properly configured. These findings suggest that privacy-preserving EHR QA systems running fully locally are feasible with current models and commodity hardware. The source code is available at https://github.com/ibrahimey/ArchEHR-QA-2026.
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。