@article{energybasedpreferencemodeloffersbetter, title = {Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model}, author = {Yuzhong Hong and Hanshan Zhang and Junwei Bao and Hongfei Jiang and Yang song}, year = {2024}, eprint = {2412.13862}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.13862v1}, }