@article{onlinepreferencealignmentforlanguage, title = {Online Preference Alignment for Language Models via Count-based Exploration}, author = {Chenjia Bai and Yang Zhang and Shuang Qiu and Qiaosheng Zhang and Kang Xu and Xuelong Li}, year = {2025}, eprint = {2501.12735}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.12735v2}, }