@article{iterativelengthregularizeddirect,
  title = {Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level},
  author = {Jie Liu and Zhanhui Zhou and Jiaheng Liu and Xingyuan Bu and Chao Yang and Han-sen Zhong and Wanli Ouyang},
  year = {2024},
  eprint = {2406.11817},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.11817v1},
}