@article{policylabeledpreferencelearningis, title = {Policy-labeled Preference Learning: Is Preference Enough for RLHF?}, author = {Taehyun Cho and Seokhun Ju and Seungyub Han and Dohyeong Kim and Kyungjae Lee and Jungwoo Lee}, year = {2025}, eprint = {2505.06273}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.06273v2}, }