English

What Formal Languages Can Transformers Express? A Survey

Machine Learning 2024-09-05 v3 Computation and Language Formal Languages and Automata Theory Logic in Computer Science

Abstract

As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providing a unified framework for harmonizing seemingly contradictory findings.

Keywords

Cite

@article{arxiv.2311.00208,
  title  = {What Formal Languages Can Transformers Express? A Survey},
  author = {Lena Strobl and William Merrill and Gail Weiss and David Chiang and Dana Angluin},
  journal= {arXiv preprint arXiv:2311.00208},
  year   = {2024}
}

Comments

One minor correction in {\S}5.1

R2 v1 2026-06-28T13:08:04.622Z