Table 1. Quantitative comparison with BERTScore between ChatDoctor and ChatGPT. The p-values in the table are derived from our paired t-test.
| ChatGPT | ChatDoctor | P-value | |
| Precision | 0.837±0.0188 | 0.8444±0.0185 |
|
| Recall | 0.8445±0.0164 | 0.8451±0.0157 |
|
| F1 Score | 0.8406±0.0143 | 0.8446±0.0138 |
|