@article{ratescorerewardmodelswithimperfect,
  title = {RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals},
  author = {David Reber and Sean Richardson and Todd Nief and Cristina Garbacea and Victor Veitch},
  year = {2024},
  eprint = {2410.11348},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.11348v3},
}