Back to Search
Start Over
MedChatZH: a Better Medical Adviser Learns from Better Instructions
- Publication Year :
- 2023
-
Abstract
- Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems. However, in specialized domains like traditional Chinese medical QA, these models may perform unsatisfactorily without fine-tuning on domain-specific datasets. To address this, we introduce MedChatZH, a dialogue model designed specifically for traditional Chinese medical QA. Our model is pre-trained on Chinese traditional medical books and fine-tuned with a carefully curated medical instruction dataset. It outperforms several solid baselines on a real-world medical dialogue dataset. We release our model, code, and dataset on https://github.com/tyang816/MedChatZH to facilitate further research in the domain of traditional Chinese medicine and LLMs.<br />Comment: 7 pages, 3 figures
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2309.01114
- Document Type :
- Working Paper