解决藏医问答中多源知识库混淆问题，提升答案可信度。
Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering
- 通过路由与预算检索，优先获取权威文献而非密集条目。
- 构建对齐图实现跨库证据融合，覆盖更全面。
- 适合需要高可信度的医疗知识问答场景。
检索增强生成（RAG）虽能实现有据回答，但在包含多个异构知识库的领域仍具挑战。在中医藏医领域，百科条目通常内容密集且易匹配，容易主导检索结果，即使经典文献或临床论文更具权威性。本文研究包含三类知识库（百科、经典、临床论文）的实际场景，并构建了500个查询的基准测试（截断阈值K=5），涵盖单源与跨源问题。提出两种互补方法：首先，DAKS通过知识库路由与预算检索，缓解密度偏差，适时优先权威来源；其次，利用对齐图引导证据融合与覆盖率感知打包，提升跨库证据覆盖，避免简单拼接。所有答案由轻量级生成器openPangu-Embedded-7B生成。实验表明，系统在路由质量与跨库证据覆盖上持续提升，全系统在CrossEv@5指标上表现最优，同时保持强忠实性与引文正确性。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) promises grounded question answering, yet domain settings with multiple heterogeneous knowledge bases (KBs) remain challenging. In Chinese Tibetan medicine, encyclopedia entries are often dense and easy to match, which can dominate retrieval even when classics or clinical papers provide more authoritative evidence. We study a practical setting with three KBs (encyclopedia, classics, and clinical papers) and a 500-query benchmark (cutoff $K{=}5$) covering both single-KB and cross-KB questions. We propose two complementary methods to improve traceability, reduce hallucinations, and enable cross-KB verification. First, DAKS performs KB routing and budgeted retrieval to mitigate density-driven bias and to prioritize authoritative sources when appropriate. Second, we use an alignment graph to guide evidence fusion and coverage-aware packing, improving cross-KB evidence coverage without relying on naive concatenation. All answers are generated by a lightweight generator, \textsc{openPangu-Embedded-7B}. Experiments show consistent gains in routing quality and cross-KB evidence coverage, with the full system achieving the best CrossEv@5 while maintaining strong faithfulness and citation correctness.
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。