The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models

• URL: http://arxiv.org/abs/2606.03645v1
• Date: Fri, 29 May 2026 10:55:50 GMT
• Title: The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models
• Abstract summary: Large Language Models exhibit paradoxical hallucination in fundamental arithmetic, implying a disconnect between internal computation and discrete output.<n>We propose the Noisy Quantization Model to explain this geometry, framing arithmetic errors as Geometric Slippages caused by internal neural noise pushing a continuous, latent Carry Potential across quantization thresholds.<n>We validate these insights through a geometric consistency check method that effectively detects and corrects these quantization failures during inference.
• Score: 11.106770083374288
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output. By analyzing the residual stream geometry during multi-operand addition, we identify the Iso-Raw-Sum Trajectory (IRST), a geometric structure where representations are anchored by semantic digits and modulated by continuous carry fibers. We propose the Noisy Quantization Model to explain this geometry, framing arithmetic errors as Geometric Slippages caused by internal neural noise pushing a continuous, latent Carry Potential across quantization thresholds. This geometric framework further elucidates Probe Versatility, explaining how lightweight probes can disentangle coexisting latent signals (such as ground truth versus hallucination) from a single activation vector. Finally, we validate these insights through a geometric consistency check method that effectively detects and corrects these quantization failures during inference. Our code is available at https://github.com/RL-MIND/Shape-of-Addition.

Related papers

• Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations [46.983222121901235]
  Generative-to-Partial Monocular Observational Alignment is a critical but under-explored challenge in computer vision.<n>We propose a training-free and interpretable geometric alignment framework that grounds generative 3D priors via a 3D similarity transformation.<n>Experiments demonstrate that our method achieves stable and accurate registration, substantially outperforming both classical geometric pipelines and state-of-the-art learning-based baselines.
  arXiv  Detail & Related papers  (2026-07-01T06:30:47Z)
• A geometric relation of the error introduced by sampling a language model's output distribution to its internal state [0.0]
  GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multiple tokens.<n>Our findings suggest that token space geometry directly reflects how models internally represent problems.
  arXiv  Detail & Related papers  (2026-05-06T13:28:16Z)
• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations [6.414826816896125]
  Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries.<n>We argue that task context operates as a non-isometric dynamical operator that enforces a necessary "topological distortion"<n>We validate this geometric evolution across a gradient of tasks, from simple mapping to complex primality testing.
  arXiv  Detail & Related papers  (2026-03-24T13:41:57Z)
• Latent Semantic Manifolds in Large Language Models [0.0]
  We develop a mathematical framework that interprets Large Language Models hidden states as points on a latent semantic manifold.<n>We prove two theorems: a rate-distortion lower bound on distortion for any finite vocabulary, and a linear volume scaling law for the expressibility gap.<n>We discuss implications for architecture design, model compression, decoding strategies, and scaling laws.
  arXiv  Detail & Related papers  (2026-03-17T13:05:56Z)
• Emergent Manifold Separability during Reasoning in Large Language Models [46.78826734548872]
  Chain-of-Thought prompting significantly improves reasoning in Large Language Models.<n>We quantify the linear separability of latent representations without the confounding factors of probe training.
  arXiv  Detail & Related papers  (2026-02-23T20:36:17Z)
• TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations [0.9179857807576733]
  Recent work has provided compelling evidence challenging the foundational manifold hypothesis for the token embedding spaces of Large Language Models.<n>We formalize this problem in the language of scheme theory and propose a rigorous resolution by applying the scheme-theoretic blow-up at each singular point.<n>We prove a formal theorem guaranteeing the geometric regularization of this new space, showing that the original pathologies are resolved.
  arXiv  Detail & Related papers  (2025-07-26T02:39:54Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning.<n>We introduce a novel approach to disentangled representation learning based on quadratic optimal transport.<n>We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• Topological Obstructions and How to Avoid Them [22.45861345237023]
  We show that local optima can arise due to singularities or an incorrect degree or winding number. We propose a new flow-based model that maps data points to multimodal distributions over geometric spaces.
  arXiv  Detail & Related papers  (2023-12-12T18:56:14Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• A Unifying and Canonical Description of Measure-Preserving Diffusions [60.59592461429012]
  A complete recipe of measure-preserving diffusions in Euclidean space was recently derived unifying several MCMC algorithms into a single framework. We develop a geometric theory that improves and generalises this construction to any manifold.
  arXiv  Detail & Related papers  (2021-05-06T17:36:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.