@inproceedings{li-etal-2025-2d, title = "2{D}-{DPO}: Scaling Direct Preference Optimization with 2-Dimensional Supervision", author = "Li, Shilong and He, Yancheng and Huang, Hui and Bu, Xingyuan and Liu, Jiaheng and Guo, Hangyu and Wang, Weixun and Gu, Jihao and Su, Wenbo and Zheng, Bo", editor = "Chiruzzo, Luis and Ritter, Alan and Wang, Lu", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/moar-dois/2025.findings-naacl.455/", doi = "10.18653/v1/2025.findings-naacl.455", pages = "8149--8173", ISBN = "979-8-89176-195-7" }