Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering
On the map: Retrieval-augmented generation → Medical and biomedical RAG
Abstract (arXiv)
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, textscopenPangu-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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 23 references that are in the map. First posted on arXiv 5 Feb 2026.
Builds on
14 of 23 references.
Closest ancestors · 2
Same direction, newest first
- 2024Benchmarking Retrieval-Augmented Generation for Medicine20 Feb
- 2023Almanac: Retrieval-Augmented Language Models for Clinical Medicine1 Mar
Other references · 12
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2023Large Language Modelscited by 780
- 2023Enabling Large Language Models to Generate Text with Citationscited by 595
- 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
- 2021CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmarkcited by 101
- 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
- 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
- 2025Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognitioncited by 62
- 2024FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generationcited by 19
- 2024DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generationcited by 16
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs
- 2025M-Eval: A Heterogeneity-Based Framework for Multi-evidence Validation in Medical RAG Systems
- 2025MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
- 2026CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
- 2026MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine
- 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
- 2026X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation
- 2025Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs