@inproceedings{kim-etal-2025-biggen, title = "The {B}i{GG}en Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models", author = "Kim, Seungone and Suk, Juyoung and Cho, Ji Yong and Longpre, Shayne and Kim, Chaeeun and Yoon, Dongkeun and Son, Guijin and Cho, Yejin and Shafayat, Sheikh and Baek, Jinheon and Park, Sue Hyun and Hwang, Hyeonbin and Jo, Jinkyung and Cho, Hyowon and Shin, Haebin and Lee, Seongyun and Oh, Hanseok and Lee, Noah and Ho, Namgyu and Joo, Se June and Ko, Miyoung and Lee, Yoonjoo and Chae, Hyungjoo and Shin, Jamin and Jang, Joel and Ye, Seonghyeon and Lin, Bill Yuchen and Welleck, Sean and Neubig, Graham and Lee, Moontae and Lee, Kyungjae and Seo, Minjoon", editor = "Chiruzzo, Luis and Ritter, Alan and Wang, Lu", booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-long.303/", pages = "5877--5919", ISBN = "979-8-89176-189-6" }