SOURCE-LINKED INTELLIGENCE

A Hyperbolicity Atlas of Large Language Model Hidden States

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of whether prompt-token hidden states in contemporary LLMs exhibit Gromov Hyperbolicity (GH), a distance-based measure of tree-likeness. Using 818,904 sample-layer measurements from ten open-weight models across MATH500, HumanEval, WinoGrande, and TruthfulQA, we build a GH map over four axes: parameter scale, layer depth, model family, and input domain. The clearest pattern is depth, not scale: middle layers usually form

Read original source ↗ Open in workspace

recordType

paper

region

Global