Authors:
(1) Chengrun Yang, Google DeepMind and Equal contribution;
(2) Xuezhi Wang, Google DeepMind;
(3) Yifeng Lu, Google DeepMind;
(4) Hanxiao Liu, Google DeepMind;
(5) Quoc V. Le, Google DeepMind;
(6) Denny Zhou, Google DeepMind;
(7) Xinyun Chen, Google DeepMind and Equal contribution.
Different optimizer models work the best on different styles of meta-prompts. Figure 3 in the main paper shows the meta-prompt for PaLM 2-L-IT; Figure 21 shows that for pre-trained PaLM 2-L; Figure 22 shows that for GPT models.