Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models

• URL: http://arxiv.org/abs/2604.06767v1
• Date: Wed, 08 Apr 2026 07:36:04 GMT
• Title: Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models
• Abstract summary: Voronoi tessellation over representation manifold investigated on Qwen3.5-4B-Base.<n>We show that Voronoi tessellation is reshapable through margin refinement procedures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models operate on discrete tokens but compute in continuous vector spaces, inducing a Voronoi tessellation over the representation manifold. We study this tessellation empirically on Qwen3.5-4B-Base, making two contributions. First, using float32 margin recomputation to resolve bfloat16 quantization artifacts, we validate Mabrok's (2026) linear scaling law of the expressibility gap with $R^2$ = 0.9997 - the strongest confirmation to date - and identify a mid-layer geometric ambiguity regime where margin geometry is anti-correlated with cross-entropy (layers 24-28, $ρ$ = -0.29) before crystallizing into alignment at the final layer ($ρ$ = 0.836). Second, we show that the Voronoi tessellation of a converged model is reshapable through margin refinement procedures (MRP): short post-hoc optimization runs that widen token-decision margins without retraining. We compare direct margin maximization against Fisher information distance maximization across a dose-response sweep. Both methods find the same ceiling of ~16,300 correctable positions per 256K evaluated, but differ critically in collateral damage. Margin maximization damage escalates with intervention strength until corrections are overwhelmed. Fisher damage remains constant at ~5,300 positions across the validated range ($λ$ = 0.15-0.6), achieving +28% median margin improvement at $λ$ = 0.6 with invariant downstream benchmarks - a geometric reorganization that compresses the expressibility gap while preserving its scaling law. However, frequency and token-class audits reveal that gains concentrate in high-frequency structural tokens (84% of net corrections at $λ$ = 0.6), with content and entity-like contributions shrinking at higher $λ$. Fisher MRP is therefore a viable geometric polishing tool whose practical ceiling is set not by aggregate damage but by the uniformity of token-level benefit.

Related papers

• Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality [0.0]
  Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures.<n>Family of edge activations derived from Banach duality maps.<n>Learnable exponents provide an interpretable, relative signal.
  arXiv  Detail & Related papers  (2026-08-26T13:53:13Z)
• Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress [0.0]
  We present the first adaptation of Pauli Correlation optimisation (PCE) to quantum topological data analysis.<n>From a Takens embedding and Vietoris--Rips filtration of S&P500 returns, we extract $0.8 Laplacians and recast null-space counting as a continuous-PCE-quotient with variational deflation.
  arXiv  Detail & Related papers  (2026-07-10T18:56:45Z)
• Hidden-State Privacy Has an Empty Middle [51.56484100374058]
  We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width.<n>A split-memory transformer trained from scratch reaches $G_mathrmMah in [20, 33]$ at 90M and maintains a $6$--$24times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language loss penalty.
  arXiv  Detail & Related papers  (2026-05-21T20:12:09Z)
• Bandit Convex Optimization with Gradient Prediction Adaptivity [56.816177049016794]
  We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
  arXiv  Detail & Related papers  (2026-05-21T08:57:38Z)
• FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers [7.108048394322025]
  Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation space is Euclidean.<n>We show this assumption fails drastically: the local geometry induced by the model's own output behavior deviates from the Euclidean metric by over 97% in relative spectral norm on GPT-2.
  arXiv  Detail & Related papers  (2026-05-17T03:00:16Z)
• Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation [45.56738584872585]
  Neural scaling laws approximate a language model's loss as a power-law function of parameter count $N$ and token count $D$.<n>We show that a collinear design induces an inherent ill-conditioning in the Gauss-Newton least-squares problem.<n>We prove this for four scaling-law formalisms and derive a closed-form TPP-diversity threshold that is necessary and sufficient for well-conditioned estimation.
  arXiv  Detail & Related papers  (2026-05-08T23:00:17Z)
• DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion [1.2031796234206138]
  DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data.<n>The framework regresses four earth-model parameters and reconstructs profiles using a differentiable soft-step decoder.<n>The framework demonstrates high robustness to noise through curriculum-based amplitude augmentation, maintaining a mean $barR2$ of 0.858 at $pm2%$ random amplitude error.
  arXiv  Detail & Related papers  (2026-05-06T14:58:17Z)
• Efficient Logistic Regression with Mixture of Sigmoids [15.14559143371469]
  We show that the near-optimal worst-case regret bound $O(dlog(Bn))$ for EW can be achieved with total worst-case computational complexity $O(B3 n5)$.<n>Our results show that EW can be both computationally tractable and geometrically adaptive in online classification.
  arXiv  Detail & Related papers  (2026-04-03T09:36:34Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Stabilizing Fixed-Point Iteration for Markov Chain Poisson Equations [49.702772230127465]
  We study finite-state Markov chains with $n$ states and transition matrix $P$.<n>We show that all non-decaying modes are captured by a real peripheral invariant subspace $mathcalK(P)$, and that the induced operator on the quotient space $mathbbRn/mathcalK(P) is strictly contractive, yielding a unique quotient solution.
  arXiv  Detail & Related papers  (2026-01-31T02:57:01Z)
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net [0.0]
  We propose a spectrally normalized surrogate for forward and inverse mechanical homogenization with hard physical guarantees.<n>In 3D linear elasticity on an open dataset of biphasic microstructures, a fully connected Voigt-Reuss net trained on $>!7.5times 105$ FFT-based labels with 236 isotropy-in descriptors.<n>Overall, the Voigt-Reuss net unifies accurate, physically admissible forward prediction with large-batch, constraint-consistent inverse design.
  arXiv  Detail & Related papers  (2025-11-14T15:17:37Z)
• Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores [3.959606869996232]
  We show that averaging TVD-MI's binary trials yields centered-probability scores with additive structure suitable for item-response theory (IRT) without nonlinear link functions.<n>We derive this clipped-linear evaluations from Gini entropy, yielding a box-constrained least-squares formulation that handles boundary saturation.
  arXiv  Detail & Related papers  (2025-10-16T17:59:25Z)
• Outcome-based Reinforcement Learning to Predict the Future [1.4313866885019229]
  We show that a compact (14B) reasoning model can be trained to match or surpass the predictive accuracy of frontier models like o1.<n>The model's performance is also practically meaningful: in a Polymarket trading simulation, we estimate that its bets would have yielded a return on investment of over 10%.
  arXiv  Detail & Related papers  (2025-05-23T14:56:07Z)
• Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification [50.717692060500696]
  Next-token prediction with the logarithmic loss is a cornerstone of autoregressive sequence modeling.<n>Next-token prediction can be made robust so as to achieve $C=tilde O(H)$, representing moderate error amplification.<n>No computationally efficient algorithm can achieve sub-polynomial approximation factor $C=e(log H)1-Omega(1)$.
  arXiv  Detail & Related papers  (2025-02-18T02:52:00Z)
• Refined Sample Complexity for Markov Games with Independent Linear Function Approximation [49.5660193419984]
  Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL) This paper first refines the AVLPR framework by Wang et al. (2023), with an insight of designing pessimistic estimation of the sub-optimality gap. We give the first algorithm that tackles the curse of multi-agents, attains the optimal $O(T-1/2) convergence rate, and avoids $textpoly(A_max)$ dependency simultaneously.
  arXiv  Detail & Related papers  (2024-02-11T01:51:15Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)

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.