@article{whatalgorithmscantransformerslearna, title = {What Algorithms can Transformers Learn? A Study in Length Generalization}, author = {Hattie Zhou and Arwen Bradley and Etai Littwin and Noam Razin and Omid Saremi and Josh Susskind and Samy Bengio and Preetum Nakkiran}, year = {2023}, eprint = {2310.16028}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.16028v1}, }