@inproceedings{hayakawa-sato-2025-theoretical,
    title = "Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding",
    author = "Hayakawa, Daichi  and
      Sato, Issei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1488/",
    pages = "30777--30834",
    ISBN = "979-8-89176-251-0",
    abstract = "In this study, we provide constructive proof that Transformers can recognize and generate hierarchical language efficiently with respect to model size, even without the need for a specific positional encoding.Specifically, we show that causal masking and a starting token enable Transformers to compute positional information and depth within hierarchical structures.We demonstrate that Transformers without positional encoding can generate hierarchical languages. Furthermore, we suggest that explicit positional encoding might have a detrimental effect on generalization with respect to sequence length."
}