@article{provablyrobustdpoaligninglanguagemodels, title = {Provably Robust DPO: Aligning Language Models with Noisy Feedback}, author = {Sayak Ray Chowdhury and Anush Kini and Nagarajan Natarajan}, year = {2024}, eprint = {2403.00409}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2403.00409v2}, }