The Role of Logic and Automata in Understanding Transformers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Anthony W., Barcelo, Pablo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909813171027968
author Lin, Anthony W.
Barcelo, Pablo
author_facet Lin, Anthony W.
Barcelo, Pablo
contents The advent of transformers has in recent years led to powerful and revolutionary Large Language Models (LLMs). Despite this, our understanding on the capability of transformers is still meager. In this invited contribution, we recount the rapid progress in the last few years to the question of what transformers can do. In particular, we will see the integral role of logic and automata (also with some help from circuit complexity) in answering this question. We also mention several open problems at the intersection of logic, automata, verification and transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24024
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Role of Logic and Automata in Understanding Transformers
Lin, Anthony W.
Barcelo, Pablo
Formal Languages and Automata Theory
Computation and Language
Machine Learning
Logic in Computer Science
The advent of transformers has in recent years led to powerful and revolutionary Large Language Models (LLMs). Despite this, our understanding on the capability of transformers is still meager. In this invited contribution, we recount the rapid progress in the last few years to the question of what transformers can do. In particular, we will see the integral role of logic and automata (also with some help from circuit complexity) in answering this question. We also mention several open problems at the intersection of logic, automata, verification and transformers.
title The Role of Logic and Automata in Understanding Transformers
topic Formal Languages and Automata Theory
Computation and Language
Machine Learning
Logic in Computer Science
url https://arxiv.org/abs/2509.24024