@article{biasfittingtomitigatelengthbiasof, title = {Bias Fitting to Mitigate Length Bias of Reward Model in RLHF}, author = {Kangwen Zhao and JianFeng Cai and Jinhua Zhu and Ruopei Sun and Dongyun Xue and Wengang Zhou and Li Li and Houqiang Li}, year = {2025}, eprint = {2505.12843}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12843v1}, }