@article{stackattentionimprovingtheabilityof,
  title = {Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns},
  author = {Brian DuSell and David Chiang},
  year = {2023},
  eprint = {2310.01749},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.01749v2},
}