accpatrick

@tshu-w @wbbeyourself @ronch99 @22842219 Thank you for your interest in our work! We are pleased to announce the release of an updated and cleaner version of the development set. To...

@tshu-w @wbbeyourself @josem7 @ronch99 Thanks for your kind reminder. We are currently starting the third round of reviews for the development set. This time, we also pay more attention to...

@tshu-w, thank you for sharing this insightful paper. We highly value such research that judges the quality of benchmarks. A similar paper from EMNLP (https://arxiv.org/pdf/2310.18538.pdf) also provides a comprehensive examination...

@MPX0222 Thanks for your interests in our work! Sorry for this issue. Actually, we wrote this just for faster evaluation since some databases are big. You could directly execute it...