@inproceedings{he-etal-2025-large, title = "Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?", author = "He, Yancheng and Li, Shilong and Liu, Jiaheng and Wang, Weixun and Bu, Xingyuan and Zhang, Ge and Peng, Z.y. and Zhang, Zhaoxiang and Zheng, Zhicheng and Su, Wenbo and Zheng, Bo", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.acl-long.905/", pages = "18468--18489", ISBN = "979-8-89176-251-0" }