%0 Journal Article %1 journals/corr/abs-2403-08635 %A Calandriello, Daniele %A Guo, Daniel %A Munos, Rémi %A Rowland, Mark %A Tang, Yunhao %A Pires, Bernardo Ávila %A Richemond, Pierre Harvey %A Lan, Charline Le %A Valko, Michal %A Liu, Tianqi %A Joshi, Rishabh %A Zheng, Zeyu %A Piot, Bilal %D 2024 %J CoRR %K dblp %T Human Alignment of Large Language Models through Online Preference Optimisation. %U http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-08635 %V abs/2403.08635

@article{journals/corr/abs-2403-08635, added-at = {2024-10-02T00:00:00.000+0200}, author = {Calandriello, Daniele and Guo, Daniel and Munos, Rémi and Rowland, Mark and Tang, Yunhao and Pires, Bernardo Ávila and Richemond, Pierre Harvey and Lan, Charline Le and Valko, Michal and Liu, Tianqi and Joshi, Rishabh and Zheng, Zeyu and Piot, Bilal}, biburl = {https://www.bibsonomy.org/bibtex/21081153d9d7eec6b891f15981bd129f4/dblp}, ee = {https://doi.org/10.48550/arXiv.2403.08635}, interhash = {edf560b4e03778fe0b9725b951670696}, intrahash = {1081153d9d7eec6b891f15981bd129f4}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-10-07T07:35:55.000+0200}, title = {Human Alignment of Large Language Models through Online Preference Optimisation.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2403.html#abs-2403-08635}, volume = {abs/2403.08635}, year = 2024 }