@article{posttraininglargelanguagemodelsviareinfo,
  title = {Post-Training Large Language Models via Reinforcement Learning from Self-Feedback},
  author = {Carel van Niekerk and Renato Vukovic and Benjamin Matthias Ruppik and Hsien-chin Lin and Milica Gašić},
  year = {2025},
  eprint = {2507.21931},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.21931},
}