%0 Generic %1 yuan2024selfrewarding %A Yuan, Weizhe %A Pang, Richard Yuanzhe %A Cho, Kyunghyun %A Sukhbaatar, Sainbayar %A Xu, Jing %A Weston, Jason %D 2024 %K low_resource nlp reinforcement_learning %T Self-Rewarding Language Models %U https://arxiv.org/abs/2401.10020

@misc{yuan2024selfrewarding, added-at = {2024-02-01T10:43:03.000+0100}, archiveprefix = {arXiv}, author = {Yuan, Weizhe and Pang, Richard Yuanzhe and Cho, Kyunghyun and Sukhbaatar, Sainbayar and Xu, Jing and Weston, Jason}, biburl = {https://www.bibsonomy.org/bibtex/242852629ab139a5ff53660506fa20fa1/jonas.kaiser}, eprint = {2401.10020}, interhash = {60527374840eb7837e0f1e0df0cc06dd}, intrahash = {42852629ab139a5ff53660506fa20fa1}, keywords = {low_resource nlp reinforcement_learning}, primaryclass = {cs.CL}, timestamp = {2024-02-01T10:47:46.000+0100}, title = {Self-Rewarding Language Models}, url = {https://arxiv.org/abs/2401.10020}, year = 2024 }