HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge

TL;DR

HuaTuo is a fine-tuned LLaMA-based model enhanced with Chinese medical knowledge, improving its accuracy and reliability in biomedical NLP tasks, especially in medical question-answering.

Contribution

The paper introduces HuaTuo, a novel biomedical LLaMA-based model fine-tuned with generated QA data to improve medical response quality in Chinese NLP tasks.

Findings

HuaTuo produces more reliable medical responses.

Fine-tuning with generated QA improves biomedical knowledge.

Model is accessible for further research.

Abstract

Large Language Models (LLMs), such as the LLaMA model, have demonstrated their effectiveness in various general-domain natural language processing (NLP) tasks. Nevertheless, LLMs have not yet performed optimally in biomedical domain tasks due to the need for medical expertise in the responses. In response to this challenge, we propose HuaTuo, a LLaMA-based model that has been supervised-fine-tuned with generated QA (Question-Answer) instances. The experimental results demonstrate that HuaTuo generates responses that possess more reliable medical knowledge. Our proposed HuaTuo model is accessible at https://github.com/SCIR-HI/Huatuo-Llama-Med-Chinese.