Can small transformers learn the language of Coxeter groups?
2611.10936

Authors

J. Elisenda Grigsby,Yiyao Huang,Arushi Katyal,Ryan Lin,Pranav Ramakrishnan

Abstract

The field of mechanistic interpretability is well-suited to collaborative projects between mathematicians and AI researchers. This work describes one such project.

We trained a small transformer to learn the language of the Coxeter group affine A2, best known as the symmetries of the tiling of the Euclidean plane by equilateral triangles. We then formulated and proved a word-theoretic conjecture about affine A2 after observing the attention patterns of the trained model.

Resources

Ray graphicRay graphicRay graphicRay graphic

Stay in the loop

Every AI paper that matters, free in your inbox daily.

Details

  • takara.ai
  • Custom AI and machine learning from the Frontier Research Team.
  • © 2026 takara.ai Ltd
  • Content is sourced from third-party publications.
Ray graphicRay graphicRay graphic