@article{beyondbinaryrewardstraininglmstoreason,
  title = {Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty},
  author = {Mehul Damani and Isha Puri and Stewart Slocum and Idan Shenfeld and Leshem Choshen and Yoon Kim and Jacob Andreas},
  year = {2025},
  eprint = {2507.16806},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.16806v1},
}