@article{chainofpreferenceoptimizationimproving, title = {Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs}, author = {Xuan Zhang and Chao Du and Tianyu Pang and Qian Liu and Wei Gao and Min Lin}, year = {2024}, eprint = {2406.09136}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.09136v2}, }