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.
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