Yaobao: An evidence-based Chinese patent medicine assistant based on large language models and multi-source datasets

Background: Chinese patent medicine (CPM) has gained increasing attention for its clinical value, but knowledge resources remain fragmented and practical digital aids are limited. Objective: To develop Yaobao, a CPM knowledge assistant whose contributions lie in domain-specific data integration and application engineering using established retrieval-augmented generation (RAG) methods. Methods: Six types of CPM resources were integrated and transformed into 95,197 question-answer pairs for a dual-level knowledge base linking semantic retrieval with source metadata. Yaobao incorporates follow-up questioning, verifiable citations, multilingual support, multimodal input, and external tool invocation. Yaobao uses DeepSeek-V3 as its generator; comparison with the standalone DeepSeek-V3 model helps assess the contribution of CPM-specific retrieval. It was compared with five general-purpose and two traditional Chinese medicine (TCM)-specific large language models on a 1,000-item single-turn benchmark, using automatic text-overlap metrics and Gemini-2.5-Pro to assess how well responses covered the reference answers. Results: Yaobao achieved the highest ROUGE-2, ROUGE-L, and METEOR scores across all three question categories and the highest ROUGE-1 scores for efficacy and prescriptions. For ROUGE-1 on precautions questions, Qwen3-235B scored 0.6771 and Yaobao scored 0.6759, while Biancang-7B achieved the highest BLEU-1 scores in all categories. Yaobao received the highest overall mean score from Gemini-2.5-Pro (3.57). Conclusions: Yaobao integrates CPM knowledge and interactive consultation features through established RAG components. On the 1,000-item benchmark, it performed strongly on questions about CPM knowledge represented in its retrieval corpus, providing a basis for further evaluation of its consultation functions.

Authors

Institutions

Publication Details

Journal
AI Evidence-Based Medicine
Published
2026-11-13
DOI
https://doi.org/10.1097/ai9.0000000000000030
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Yaobao: An evidence-based Chinese patent medicine assistant based on large language models and multi-source datasets

Zeming Li, Lu Zhang, Aiping Lyu, Yingqiao Zhang et al.
5 links
AI Evidence-Based Medicine
Artificial Intelligence in Healthcare and Education
article

Yaobao: An evidence-based Chinese patent medicine assistant based on large language models and multi-source datasets

Zeming Li, Lu Zhang, Aiping Lyu, Yingqiao Zhang, Hiufung Yip, Zhenfeng Wu, Bo Han
article en

Abstract

Background: Chinese patent medicine (CPM) has gained increasing attention for its clinical value, but knowledge resources remain fragmented and practical digital aids are limited. Objective: To develop Yaobao, a CPM knowledge assistant whose contributions lie in domain-specific data integration and application engineering using established retrieval-augmented generation (RAG) methods. Methods: Six types of CPM resources were integrated and transformed into 95,197 question-answer pairs for a dual-level knowledge base linking semantic retrieval with source metadata. Yaobao incorporates follow-up questioning, verifiable citations, multilingual support, multimodal input, and external tool invocation. Yaobao uses DeepSeek-V3 as its generator; comparison with the standalone DeepSeek-V3 model helps assess the contribution of CPM-specific retrieval. It was compared with five general-purpose and two traditional Chinese medicine (TCM)-specific large language models on a 1,000-item single-turn benchmark, using automatic text-overlap metrics and Gemini-2.5-Pro to assess how well responses covered the reference answers. Results: Yaobao achieved the highest ROUGE-2, ROUGE-L, and METEOR scores across all three question categories and the highest ROUGE-1 scores for efficacy and prescriptions. For ROUGE-1 on precautions questions, Qwen3-235B scored 0.6771 and Yaobao scored 0.6759, while Biancang-7B achieved the highest BLEU-1 scores in all categories. Yaobao received the highest overall mean score from Gemini-2.5-Pro (3.57). Conclusions: Yaobao integrates CPM knowledge and interactive consultation features through established RAG components. On the 1,000-item benchmark, it performed strongly on questions about CPM knowledge represented in its retrieval corpus, providing a basis for further evaluation of its consultation functions.

AI Evidence-Based Medicine
Jiangxi University of Traditional Chinese Medicine (CN), Hong Kong Baptist University (HK)
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon