Releasing Evaluation Prompts?

#2
by kevinyaoresearch - opened

I can't find the Github link claimed in the paper. Do the authors plan to release the code?

In addition, is there any plan to release the (completion-based and token-probability-based) prompts used in the evaluation? The description in Appendix 6.2.1 isn't clear to me. How is the "300-word long chunk" used in Figure 11? What's meant by " followed by a list of hand-curated examples"? Do you need to manually write examples to show how to create prompts based on the 300-word original text chunk?

Sign up or log in to comment