@article{aligninglanguagemodelsusingfollowup,
  title = {Aligning Language Models Using Follow-up Likelihood as Reward Signal},
  author = {Chen Zhang and Dading Chong and Feng Jiang and Chengguang Tang and Anningzhe Gao and Guohua Tang and Haizhou Li},
  year = {2024},
  eprint = {2409.13948},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.13948v2},
}