MAM-AI：面向桑给巴尔护士和助产士的设备端医疗检索增强生成系统
MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar
AI总结：
针对撒哈拉以南非洲地区护士助产士难以获取权威指南的问题，提出完全运行于安卓设备上的医疗问答系统MAM-AI，采用300M嵌入模型检索87份指南文档，并用4B int4生成器离线生成带引用的回答，评估发现小生成器在安全性和有用性间存在权衡，通过优化提示词降低回避率。
摘要：
撒哈拉以南非洲地区的孕产妇和新生儿死亡率仍然居高不下，助产护理通常由缺乏国际标准助产培训的护士提供，且在护理点查阅权威指南十分困难：指南冗长且网络连接不稳定。我们提出MAM-AI，一个面向桑给巴尔护士助产士的医疗问答助手，完全运行于普通安卓设备上：将问题嵌入（EmbeddingGemma，300M）并与包含87份指南文档（63,650个段落）的精选语料库进行匹配，然后由4B int4生成器（Gemma 4 E4B）完全离线生成带引用的回答，查询不会离开设备。我们采用分层方法（检索器、在oracle上下文下的生成器、端到端和延迟）评估实际部署配置，由经过医生评分标准验证的LLM评判员打分。评估重新定位了难题。设备端检索基本解决：300M嵌入器在七个检索器中排名第三，可与云系统媲美，因此系统所需的段落通常能找到。小生成器仍是问题所在：添加检索上下文并未改善其回答，且4B模型无法同时做到有用和安全——在两个相同规模的候选模型中，更有用的那个会犯真正的危险错误，因此我们部署了另一个，其对来源的忠实度约为前者的两倍（与前沿模型相当），并通过重新设计的提示词恢复其有用性，将回避率从33%降至3%。出于同样原因，语料库质量至关重要：当语料库包含正确段落时，回答具体且可操作；否则回答含糊不清。MAM-AI是一个经过充分评估的开源研究原型，而非已部署的产品；系统、知识库、基准测试和评估工具均已发布。
英文摘要：
Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery training to international standards, and consulting authoritative guidance at the point of care is hard: the guidelines are long and connectivity is intermittent. We present MAM-AI, a medical question-answering assistant for nurse-midwives in Zanzibar that runs entirely on a commodity Android device: a question is embedded (EmbeddingGemma, 300M) and matched against a curated corpus of 87 guideline documents (63,650 passages), then answered with citations by a 4B int4 generator (Gemma 4 E4B), fully offline, with no query leaving the device. We evaluate the exact deployed configuration with a layered methodology -- retriever, generator under oracle context, end-to-end, and latency -- scored by LLM judges validated against physician rubrics. The evaluation relocates the hard problem. On-device retrieval is essentially solved: the 300M embedder ranks third of seven retrievers and rivals cloud systems, so the passages the system needs are usually found. The small generator is what remains in doubt: adding retrieved context does not improve its answers, and at 4B it cannot be both helpful and safe at once -- of two same-size candidates, the more helpful one commits genuine dangerous errors, so we deploy the other, which is about twice as faithful to its sources (as faithful as a frontier model), and recover its helpfulness with a redesigned prompt that cuts deflection from 33% to 3%. Corpus quality is decisive for the same reason: where the corpus holds the right passage the answer is specific and actionable, and where it does not it goes vague. MAM-AI is a thoroughly evaluated, open-source research prototype, not a fielded product; the system, knowledge base, benchmarks, and evaluation harness are released.
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。
