@misc{barbero2024transformers, title={Transformers need glasses! Information over-squashing in language tasks}, author={Federico Barbero and Andrea Banino and Steven Kapturowski and Dharshan Kumaran and João G. M. Araújo and Alex Vitvitskyi and Razvan Pascanu and Petar Veličković}, year={2024}, eprint={2406.04267}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2406.04267} }