@article{tisdpotokenlevelimportancesamplingfor, title = {TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights}, author = {Aiwei Liu and Haoping Bai and Zhiyun Lu and Yanchao Sun and Xiang Kong and Simon Wang and Jiulong Shan and Albin Madappally Jose and Xiaojiang Liu and Lijie Wen and Philip S. Yu and Meng Cao}, year = {2024}, eprint = {2410.04350}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.04350v3}, }