where are the In-context problem refining examples?

[cosmicexotic]

i.e. (1) remove irrelevant information, as the first refining step in Figure 2; (2) rearrange the logic structure and group relevant conditions together, as the second rephrasing step in Figure 2; (3) summarize local conditions into new ones in parallel, as the third rephrasing step in Figure 2. 3 Next, we use prompting methods in Sec. 2 to get the final answer. Preliminary results show that in-context problem refining yields more performance gain than zeroshot refining.

thanks for any reply.