arXiv · 2611.10936
Can small transformers learn the language of Coxeter groups?
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
J. Elisenda Grigsby, Yiyao Huang, Arushi Katyal, Ryan Lin, Pranav Ramakrishnan, Weiya Wang. 2026-11-07. Can small transformers learn the language of Coxeter groups?. https://searcharxiv.com/abs/2611.10936
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.