Closed allanj closed 1 year ago
In the appendix, the original PAL with ChatGPT is around 74%.
But how come the initial accuracy is only 71% in self-refine, I was expecting the initial should be the same?
Thanks for pointing this out. The results in Figure 14 use code-davinci-002 (codex), which match the numbers reported in PaL (72%). We will clarify this in the next update.
In the appendix, the original PAL with ChatGPT is around 74%.
But how come the initial accuracy is only 71% in self-refine, I was expecting the initial should be the same?