@article{prototypicalrewardnetworkfordata, title = {Prototypical Reward Network for Data-Efficient RLHF}, author = {Jinghan Zhang and Xiting Wang and Yiqiao Jin and Changyu Chen and Xinhao Zhang and Kunpeng Liu}, year = {2024}, eprint = {2406.06606}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.06606v2}, }