MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis

doi:10.1016/j.eswa.2025.130905

CSpace

	MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis
	Lv, Bo 1,2,3; Tang, Chen 4; Liu, Nayu 5; Yu, Guoxin 2; Liu, Xin 2; Zhang, Riyan 6; Yu, Yue 2
	2026-04-05
发表期刊	EXPERT SYSTEMS WITH APPLICATIONS
ISSN	0957-4174
卷号	305 页码:15
摘要	In recent years, deep-learning-based approaches for medical dialogue generation have become the predominant paradigm. However, real-world medical dialogues often face data imbalance issues, especially long-tail distribution problems. The scarcity of training samples for low-resource diseases makes it challenging for language models to provide accurate and comprehensive diagnostic support. In this paper, we propose MIRE, a novel framework that leverages external medical knowledge of tail diseases and dialogue data of common diseases to guide large language models (LLMs) in generating synthetic dialogues for tail diseases. Specifically, MIRE retrieves and crawls medical information about tail diseases from multiple online sources, enhancing subtype coverage in the generated synthetic dialogues. Moreover, we introduce a style transfer mechanism that utilises rich style templates extracted from common disease conversations to guide LLMs in augmenting dialogues in low-resource domains, thereby narrowing the gap between synthetic and real human dialogues. To evaluate the effectiveness of our method in addressing the long-tail disease problems, we construct a long-tail medical dialogue dataset, named TailMed. Experimental results show that training the model with a mixture of synthetic dialogues and the original dataset significantly improves both automatic metrics and human evaluations. Specifically, the model trained on the MIRE-enhanced dataset outperforms the original by over 20% in average metrics for tail diseases. These results demonstrate the potential of MIRE to enhance clinical dialogue systems, enabling more equitable diagnostic assistance for rare and underrepresented diseases, and contributing to improved accessibility in intelligent healthcare applications.
关键词	Long-tail medical dialogue synthetic Large language models (LLMs) Synthetic data generation External medical knowledge Style transfer
DOI	10.1016/j.eswa.2025.130905
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Operations Research & Management Science
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS记录号	WOS:001656137500001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42914
专题	中国科学院计算技术研究所
通讯作者	Liu, Nayu; Yu, Yue
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing, Peoples R China 2.Peng Cheng Lab, Shenzhen, Peoples R China 3.Univ Chinese Acad Sci, Shenyang, Peoples R China 4.Inst Adv Algorithms Res, Shanghai, Peoples R China 5.Tiangong Univ, Sch Comp Sci & Technol, Tianjin Key Lab Autonomous Intelligence Technol &, Tianjin, Peoples R China 6.Wenzhou Med Univ, Wenzhou, Peoples R China
推荐引用方式 GB/T 7714	Lv, Bo,Tang, Chen,Liu, Nayu,et al. MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis[J]. EXPERT SYSTEMS WITH APPLICATIONS,2026,305:15.
APA	Lv, Bo.,Tang, Chen.,Liu, Nayu.,Yu, Guoxin.,Liu, Xin.,...&Yu, Yue.(2026).MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis.EXPERT SYSTEMS WITH APPLICATIONS,305,15.
MLA	Lv, Bo,et al."MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis".EXPERT SYSTEMS WITH APPLICATIONS 305(2026):15.