@article{reinforcementlearningfromreflective,
  title = {Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection},
  author = {Kyungjae Lee and Dasol Hwang and Sunghyun Park and Youngsoo Jang and Moontae Lee},
  year = {2024},
  eprint = {2403.14238},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.14238v1},
}