@misc{razin2024unintentional, title={Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization}, author={Noam Razin and Sadhika Malladi and Adithya Bhaskar and Danqi Chen and Sanjeev Arora and Boris Hanin}, year={2024}, eprint={2410.08847}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2410.08847} }