@misc{zhang2025reward, title={RAG-Reward: Optimizing RAG with Reward Modeling and RLHF}, author={Hanning Zhang and Juntong Song and Juno Zhu and Yuanhao Wu and Tong Zhang and Cheng Niu}, year={2025}, eprint={2501.13264}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2501.13264} }