@article{dynamicrewardingwithpromptoptimization,
  title = {Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models},
  author = {Somanshu Singla and Zhen Wang and Tianyang Liu and Abdullah Ashfaq and Zhiting Hu and Eric P. Xing},
  year = {2024},
  eprint = {2411.08733},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.08733v2},
}