@article{disentanglinglengthfromqualityindirect, title = {Disentangling Length from Quality in Direct Preference Optimization}, author = {Ryan Park and Rafael Rafailov and Stefano Ermon and Chelsea Finn}, year = {2024}, eprint = {2403.19159}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.19159v2}, }