arXiv cs.LGOctober 2, 2026
Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
Excerpt
arXiv:2610.00647v1 Announce Type: new Abstract: The representations that language models learn for concepts such as months, weekdays, and places display consistent geometric structure: circles and saddle-shaped "Pringle" manifolds. Recent work traced these structures to $\textit{translation symmetry}$ in word co-occurrence statistics, deriving the observed Fourier geometry when co-occurrence depends only on distance on an abelian lattice of concepts. We demonstrate that more general notions of s