@article{preferenceoptimizationforreasoningwith, title = {Preference Optimization for Reasoning with Pseudo Feedback}, author = {Fangkai Jiao and Geyang Guo and Xingxing Zhang and Nancy F. Chen and Shafiq Joty and Furu Wei}, year = {2024}, eprint = {2411.16345}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.16345v1}, }