The Effect of Masking Strategies on Knowledge Retention by Language Models

@misc{wallat2023effect,
  title = {The Effect of Masking Strategies on Knowledge Retention by Language Models},
  author = {Jonas Wallat and Tianyi Zhang and Avishek Anand},
  year = {2023},
  eprint = {2306.07185},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.07185},
}