Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese

TL;DR

This paper introduces a knowledge-tuning approach using structured medical knowledge bases to improve the accuracy and reliability of Chinese medical response generation by large language models, addressing hallucination issues.

Contribution

It proposes a novel knowledge-tuning method leveraging structured medical knowledge bases and releases a Chinese medical QA dataset for domain-specific evaluation.

Findings

Knowledge-tuned LLMs outperform vanilla instruction-tuned models in medical accuracy.

The approach reduces hallucinations in medical responses.

cMedKnowQA effectively assesses medical knowledge proficiency.

Abstract

Large Language Models (LLMs) have demonstrated remarkable success in diverse natural language processing (NLP) tasks in general domains. However, LLMs sometimes generate responses with the hallucination about medical facts due to limited domain knowledge. Such shortcomings pose potential risks in the utilization of LLMs within medical contexts. To address this challenge, we propose knowledge-tuning, which leverages structured medical knowledge bases for the LLMs to grasp domain knowledge efficiently and facilitate reliable response generation. We also release cMedKnowQA, a Chinese medical knowledge question-answering dataset constructed from medical knowledge bases to assess the medical knowledge proficiency of LLMs. Experimental results show that the LLMs which are knowledge-tuned with cMedKnowQA, can exhibit higher levels of accuracy in response generation compared with vanilla instruction-tuning and offer a new reliable way for the domain adaptation of LLMs.