MIRE: A medical information enhanced framework for long-tail medical dialogue synthesis
文献类型：期刊论文
| 作者 | Lv, Bo4,5,6; Tang, Chen1; Liu, Nayu2; Yu, Guoxin5; Liu, Xin5; Zhang, Riyan3; Yu, Yue5 |
| 刊名 | EXPERT SYSTEMS WITH APPLICATIONS
 |
| 出版日期 | 2026-04-05 |
| 卷号 | 305页码:15 |
| 关键词 | Long-tail medical dialogue synthetic Large language models (LLMs) Synthetic data generation External medical knowledge Style transfer |
| ISSN号 | 0957-4174 |
| DOI | 10.1016/j.eswa.2025.130905 |
| 英文摘要 | 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. |
| WOS研究方向 | Computer Science ; Engineering ; Operations Research & Management Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001656137500001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42913]  |
| 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.Inst Adv Algorithms Res, Shanghai, Peoples R China 2.Tiangong Univ, Sch Comp Sci & Technol, Tianjin Key Lab Autonomous Intelligence Technol &, Tianjin, Peoples R China 3.Wenzhou Med Univ, Wenzhou, Peoples R China 4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing, Peoples R China 5.Peng Cheng Lab, Shenzhen, Peoples R China 6.Univ Chinese Acad Sci, Shenyang, 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. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。