@article{whydosmalllanguagemodelsunderperform,
  title = {Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck},
  author = {Nathan Godey and Éric de la Clergerie and Benoît Sagot},
  year = {2024},
  eprint = {2404.07647},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.07647v1},
}