Are we going to release all the test data as benchmark once the challenge is concluded?

Just out of curiosity.

Also, I am new to the field, is there are a official recommended list of good public benchmark data (similar domain, but of course different source) that I can used to iterate my model?


I’m also hoping that CRAG’s private test set will be made public after the challenge so that I can experiment more. As for other public datasets, you might want to refer to the Related Work section of the homepage: AIcrowd | Meta Comprehensive RAG Benchmark: KDD Cup 2024 | Challenges

This is the main page. I don’t see anything mentioning available dataset.

Wrong link?