@article{uncertaintypenalizeddirectpreference, title = {Uncertainty-Penalized Direct Preference Optimization}, author = {Sam Houliston and Alizée Pace and Alexander Immer and Gunnar Rätsch}, year = {2024}, eprint = {2410.20187}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.20187v1}, }