@article{counteringrewardoveroptimizationinllm,
  title = {Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning},
  author = {Mathieu Rita and Florian Strub and Rahma Chaabouni and Paul Michel and Emmanuel Dupoux and Olivier Pietquin},
  year = {2024},
  eprint = {2404.19409},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.19409v1},
}