@misc{pan2023rewards,
  title={Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark},
  author={Alexander Pan and Chan Jun Shern and Andy Zou and Nathaniel Li and Steven Basart and Thomas Woodside and Jonathan Ng and Hanlin Zhang and Scott Emmons and Dan Hendrycks},
  year={2023},
  eprint={2304.03279},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2304.03279}
}