Medical Knowledge Q&A Evaluation Based on ChatGPT Ensemble Learning

In the medical field, there is a large amount of clinical medical data, and a lot of knowledge is hidden in it. In recent years, the rapid development of Large Language Models (LLMs) has also affected the development of the medical field. And the application of LLMs has made computer-aided medical diagnosis possible. However, it is critical to ensure the accuracy and reliability of these models in clinical applications. This paper describes our participation in Task 4 of the China Conference on Health Information Processing (CHIP 2023). We propose a framework based on ChatGPT fusion ensemble learning to achieve question answering in medical domain. Experimental results show that our framework has excellent performance, with the Precision of 0.77, the Recall of 0.76, and the F1 of 0.76 in test dataset.