@inproceedings{simulatingbanditlearningfromuserfeedback,
  title = {Simulating Bandit Learning from User Feedback for Extractive Question Answering},
  author = {Ge Gao and Eunsol Choi and Yoav Artzi},
  year = {2022},
  booktitle = {ACL 2022 5},
  eprint = {2203.10079},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.10079v1},
}