Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering

TL;DR

This paper introduces a novel retrieval-augmented generation framework for Chinese Tibetan medicine question answering, effectively managing multiple heterogeneous knowledge bases to improve answer accuracy, traceability, and evidence coverage.

Contribution

It proposes two methods, DAKS and an alignment graph, to enhance KB routing, evidence fusion, and cross-KB verification in a multi-source RAG setting.

Findings

Improved routing quality and evidence coverage.

Achieved best CrossEv@5 performance.

Maintained high faithfulness and citation correctness.

Abstract

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.