LGMay 6

A geometric relation of the error introduced by sampling a language model's output distribution to its internal state

arXiv:2605.0489949.9
AI Analysis

Provides a geometric framework linking token-level sensitivity to model internals, offering a new lens for understanding language model behavior.

The paper derives a geometric 1-form from token embeddings that captures sensitivity to single-token changes in GPT models, and shows its curvature correlates with semantic structure in chess reasoning tasks, indicating that token space geometry reflects internal problem representations.

GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multiple tokens. Viewing this sensitivity as a geometric property, we derive an $\mathfrak{so}(n)$-valued 1-form that depends only on the geometry of the token embeddings. Despite this purely geometric origin, we show that its curvature is semantically meaningful: On chess reasoning tasks, the curvature couples to the world model of an off-the-shelf instruction-tuned model, with transformations clustering by board region and respecting piece importance. Our findings suggest that token space geometry directly reflects how models internally represent problems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes