Transformers are Inherently Succinct

Published 22 Oct 2025 in cs.FL, cs.LG, and cs.LO | (2510.19315v1)

Abstract: We propose succinctness as a measure of the expressive power of a transformer in describing a concept. To this end, we prove that transformers are highly expressive in that they can represent formal languages substantially more succinctly than standard representations of formal languages like finite automata and Linear Temporal Logic (LTL) formulas. As a by-product of this expressivity, we show that verifying properties of transformers is provably intractable (i.e. EXPSPACE-complete).

Abstract PDF Chat (Pro)

Summary

We haven't generated a summary for this paper yet.

Whiteboard

Generate a whiteboard explanation of this paper.

Sign Up to Generate

Paper to Video (Beta)

Generate a video overview of this paper.

Sign Up to Generate

Paper Prompts

Sign up for free to create and run prompts on this paper using GPT-5.

Top Community Prompts

Explain it Like I'm 14

Practical Applications

Conceptual Simplification

Sign Up to Activate View All Prompts

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Authors (3)

Collections

Sign up for free to add this paper to one or more collections.