%0 Journal Article %1 journals/corr/abs-2311-09641 %A Wang, Jiongxiao %A Wu, Junlin %A Chen, Muhao %A Vorobeychik, Yevgeniy %A Xiao, Chaowei %D 2023 %J CoRR %K dblp %T On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2311.html#abs-2311-09641 %V abs/2311.09641

@article{journals/corr/abs-2311-09641, added-at = {2023-11-21T00:00:00.000+0100}, author = {Wang, Jiongxiao and Wu, Junlin and Chen, Muhao and Vorobeychik, Yevgeniy and Xiao, Chaowei}, biburl = {https://www.bibsonomy.org/bibtex/290c792ad480ed85964180f78cea1cbec/dblp}, ee = {https://doi.org/10.48550/arXiv.2311.09641}, interhash = {786939843b0ce151863fa546bec576ed}, intrahash = {90c792ad480ed85964180f78cea1cbec}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:35:06.000+0200}, title = {On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2311.html#abs-2311-09641}, volume = {abs/2311.09641}, year = 2023 }