@article{rewardrobustrlhfinllms, title = {Reward-Robust RLHF in LLMs}, author = {Yuzi Yan and Xingzhou Lou and Jialian Li and Yiping Zhang and Jian Xie and Chao Yu and Yu Wang and Dong Yan and Yuan Shen}, year = {2024}, eprint = {2409.15360}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.15360v3}, }