@article{onsymmetriclossesforrobustpolicy, title = {On Symmetric Losses for Robust Policy Optimization with Noisy Preferences}, author = {Soichiro Nishimori and Yu-Jie Zhang and Thanawat Lodkaew and Masashi Sugiyama}, year = {2025}, eprint = {2505.24709}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24709v1}, }