构建安全约束的LLM系统，精准提供母婴健康信息。
Designing Safety-Constrained LLM Systems for Public Health Information Access
- 多层架构结合受限检索增强生成与严格边界控制。
- 响应平均耗时5.3秒，确保信息始终源自权威资源。
- 适合医疗等需严格信息边界与可审计性的场景。
我们设计并实现了一个面向公共健康信息获取的安全约束型大语言模型（LLM）系统，聚焦于母婴健康（MCH）资源导航。尽管基于LLM的系统提供灵活自然的信息检索接口，但其在医疗场景中的部署会带来安全、信任和不可控生成的风险。本文探索了在安全关键环境中约束LLM行为的实用设计模式。提出一种多层架构，集成领域限定的检索增强生成（RAG）、防止医疗建议的严格边界控制、匿名多用户会话管理以及全面的审计日志以支持监控与合规。设计核心是受控数据管道，确保所有响应均基于精心筛选的公共卫生资源，避免依赖模型预训练的医学知识。系统已在真实公共健康场景中部署，并通过涵盖范围内外及紧急查询的场景化验证。结果表明，安全约束得到一致执行，资源溯源可靠，系统性能稳定，平均响应时间为5.3秒。此外，我们讨论了在安全性、可用性与灵活性之间权衡的设计取舍与经验教训，为在医疗及其他需严格信息边界与问责制的领域部署基于LLM的系统提供了实践指导。
原文摘要 · Abstract (English)
We present the design and implementation of a safety constrained large language model (LLM) system for public health information access, focusing on maternal and child health (MCH) resource navigation. While LLM based systems offer flexible and natural interfaces for information retrieval, their deployment in healthcare contexts introduces risks related to safety, trust, and uncontrolled generation. This work explores practical design patterns for constraining LLM behavior in safety critical environments. We introduce a multi-layered architecture that integrates domain-restricted retrieval augmented generation (RAG), strict boundary enforcement to prevent medical advice, anonymous multiuser session management, and comprehensive audit logging for monitoring and compliance. A key aspect of the design is a controlled data pipeline that grounds all responses in curated public health resources, avoiding reliance on the model pretrained medical knowledge. We implement the system in a real world public health setting and conduct scenario-based validation across in scope, out of scope, and emergency queries. Results show consistent enforcement of safety constraints, reliable resource grounding, and stable system performance, with an average response time of 5.3 seconds. Beyond the specific application, we discuss design trade offs and lessons learned in balancing safety, usability, and system flexibility. Our findings provide practical guidance for deploying LLM based systems in healthcare and other domains where strict information boundaries and accountability are required.
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。