@article{headlesslanguagemodelslearningwithout,
  title = {Headless Language Models: Learning without Predicting with Contrastive Weight Tying},
  author = {Nathan Godey and Éric de la Clergerie and Benoît Sagot},
  year = {2023},
  eprint = {2309.08351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.08351v1},
}