@article{brainbayesianrewardconditionedamortized,
  title = {BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback},
  author = {Gaurav Pandey and Yatin Nandwani and Tahira Naseem and Mayank Mishra and Guangxuan Xu and Dinesh Raghu and Sachindra Joshi and Asim Munawar and Ramón Fernandez Astudillo},
  year = {2024},
  eprint = {2402.02479},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.02479v2},
}