@article{rewardmodelingwithweaksupervisionfor,
  title = {Reward Modeling with Weak Supervision for Language Models},
  author = {Ben Hauptvogel and Malte Ostendorff and Georg Rehm and Sebastian Möller},
  year = {2024},
  eprint = {2410.20869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.20869v1},
}