@article{beyondscalarrewardmodellearning, title = {Beyond Scalar Reward Model: Learning Generative Judge from Preference Data}, author = {Ziyi Ye and Xiangsheng Li and Qiuchi Li and Qingyao Ai and Yujia Zhou and Wei Shen and Dong Yan and Yiqun Liu}, year = {2024}, eprint = {2410.03742}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.03742v2}, }