TSWAP用检索增强生成技术，打造多语言泰式健康顾问。
TSWAP: A Multilingual Retrieval-Augmented Thai Wellness Advisor
- 用混合稠密-稀疏检索+交叉编码重排序，实现精准知识召回。
- 在50个问题上召回率达88%，91.1%的问答测试复现通过。
- 首次发布泰医健康检索基准，适合跨语言医疗系统研究者。
我们提出TSWAP，一个部署中的八语言对话式健康顾问，基于检索增强生成技术，依托经验证的泰国传统医学与认证健康服务提供者知识库。采用未修改的开源大模型（Qwen3.6-35B-A3B on vLLM），通过约30.6千块的泰语索引，结合混合稠密-稀疏检索器及交叉编码重排序进行知识定位；首轮查询分类器强制工具调用以查找实体；规则化安全层确保医疗范围与泰国紧急转诊；所有八种语言均通过零样本“翻译后检索”支持。我们发布了首个泰医/健康检索基准（50个问题，黄金文档标签；Recall@5=0.88）、生产级问答日志（259例中91.1%测试复现通过），以及71个无检索探针问题，揭示各模块贡献：若无安全提示，后端模型会生成完整药物剂量方案并响应超域请求；若无知识库，则无法生成可验证的服务提供者推荐。还报告两项可迁移部署发现：英语校准的4比特AWQ量化会破坏泰语声调标记，且强制检索路由对可靠知识接地至关重要。
原文摘要 · Abstract (English)
We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base of Thai traditional medicine and certified wellness providers. An unmodified open-weight LLM (Qwen3.6-35B-A3B on vLLM) is grounded on a ~30.6K-chunk Thai index by a hybrid dense-sparse retriever with cross-encoder reranking; a first-turn query classifier forces tool-based retrieval for entity lookups; a rule-based safety layer enforces medical scope and Thai emergency routing; and all eight languages are served zero-shot with translate-then-retrieve. We release the first Thai traditional-medicine/wellness retrieval benchmark (50 questions with gold document IDs; Recall@5 = 0.88), production QA logs (91.1% test-retest pass over 259 cases), and a 71-question frontier no-retrieval probe showing what each grounding pillar contributes: without the safety prompt the backend model family produced a full drug-dosing schedule and complied with out-of-scope requests, and without the knowledge base it produced zero verifiable provider recommendations. We further report two transferable deployment findings: English-calibrated 4-bit AWQ quantization corrupts Thai tone marks, and forced-retrieval routing is necessary for reliable grounding.
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。