@article{reinforcementlearningfromhumanfeedback, title = {Reinforcement Learning from Human Feedback with Active Queries}, author = {Kaixuan Ji and Jiafan He and Quanquan Gu}, year = {2024}, eprint = {2402.09401}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.09401v2}, }