will you release the code making the eval data?

[menghonghan]

Awesome work! Will you release the code that creates your eval dataset because it's quite complicated from your description in the paper. Using this method to generate more data for further instruction following finetuning could be promising.

[YJiangcm]

Thanks for your interest in our work! We construct FollowBench relying on human annotation in most cases. Only the data falling into the category of "example constraint" is generated using code. We have released the code at create_example_constraint.py.