@article{reinforcementlearningfromllmfeedbackto,
  title = {Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization},
  author = {Houda Nait El Barj and Theophile Sautory},
  year = {2024},
  eprint = {2401.07181},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.07181v1},
}