The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations

• URL: http://arxiv.org/abs/2603.23577v1
• Date: Tue, 24 Mar 2026 13:41:57 GMT
• Title: The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations
• Abstract summary: 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.
• Score: 6.414826816896125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries. Prevailing theories relying on linear isometric projections fail to resolve this fundamental tension. In this work, we argue that task context operates as a non-isometric dynamical operator that enforces a necessary "topological distortion." By applying Gram-Schmidt decomposition to residual-stream activations , we reveal a dual-modulation mechanism driving this process: a class-agnostic topological preservation that anchors global structure to prevent semantic collapse, and a specific algebraic divergence that directionally tears apart cross-class concepts to forge logical boundaries. We validate this geometric evolution across a gradient of tasks, from simple mapping to complex primality testing. Crucially, targeted specific vector ablation establishes a strict causal binding between this topology and model function: algebraically erasing the divergence component collapses parity classification accuracy from 100% to chance levels (38.57%). Furthermore, we uncover a three-phase layer-wise geometric dynamic and demonstrate that under social pressure prompts, models fail to generate sufficient divergence. This results in a "manifold entanglement" that geometrically explains sycophancy and hallucination. Ultimately, our findings revise the linear-isometric presumption, demonstrating that the emergence of discrete logic in LLMs is purchased at an irreducible cost of topological deformation.

Related papers

• Reasoning emerges from constrained inference manifolds in large language models [98.6966322378456]
  We study reasoning as an intrinsic dynamical process by examining the evolution of internal representations during inference.<n>We find that such geometric compression, although pervasive, is not sufficient for stable or reliable reasoning.
  arXiv  Detail & Related papers  (2026-05-02T10:41:20Z)
• Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models [7.073238726507493]
  We formalize structural causal models as cellular sheaves over Wasserstein spaces.<n>To ensure tractability, we introduce entropic regularization and derive the Entropic Wasserstein Causal Sheaf Laplacian.<n>Our framework successfully leverages thermodynamic noise to navigate topological barriers in high-dimensional scRNA-seq counterfactuals.
  arXiv  Detail & Related papers  (2026-03-18T06:07:07Z)
• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• 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)
• Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution [3.0242762196828448]
  Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory.<n>We show that models do not "unlearn" or suppress the magnitude of internal truths but rather employ a mechanism of geometric displacement.
  arXiv  Detail & Related papers  (2026-02-04T06:13:11Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• Manifold Percolation: from generative model to Reinforce learning [0.26905021039717986]
  Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task becomes disentangling the geometric support from the probability distribution.<n>We propose that continuum percolation is uniquely suited to this support analysis, as the sampling process effectively projects high-dimensional density estimation onto a geometric counting problem on the support.
  arXiv  Detail & Related papers  (2025-11-25T17:12:42Z)
• 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)
• Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning [73.18052192964349]
  We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics.<n>By lifting neural parameters to a measure space and modeling training as Wasserstein gradient flow, we show that under geometric constraints, the parameter measure $mu_t$ undergoes two concurrent phenomena.
  arXiv  Detail & Related papers  (2025-06-26T22:40:30Z)
• Relative Representations: Topological and Geometric Perspectives [50.85040046976025]
  Relative representations are an established approach to zero-shot model stitching.<n>We introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations.<n>Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes.
  arXiv  Detail & Related papers  (2024-09-17T08:09:22Z)

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.