The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers Reason

• URL: http://arxiv.org/abs/2604.15350v1
• Date: Fri, 03 Apr 2026 09:18:57 GMT
• Title: The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers Reason
• Abstract summary: We find that large language models exhibit emphspectral phase transitions in their hidden activation spaces when engaging in reasoning versus factual recall.<n>We establish a comprehensive emphspectral theory of reasoning in transformers, revealing that the geometry of thought is universal in direction, architecture-specific, and predictive of outcome.
• Score: 4.28787537081191
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We discover that large language models exhibit \emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systematic spectral analysis across \textbf{11 models} spanning \textbf{5 architecture families} (Qwen, Pythia, Phi, Llama, DeepSeek-R1), we identify \textbf{seven} core phenomena: (1)~\textbf{Reasoning Spectral Compression} -- 9/11 models show significantly lower $α$ for reasoning ($p < 0.05$), with larger effects in stronger models; (2)~\textbf{Instruction Tuning Spectral Reversal} -- base models show reasoning $α< $ factual $α$, while instruction-tuned models reverse this relationship; (3)~\textbf{Architecture-Dependent Generation Taxonomy} -- prompt-to-response shifts partition into expansion, compression, and equilibrium regimes; (4)~\textbf{Spectral Scaling Law} -- $α_\text{reasoning} \propto -0.074 \ln N$ across 4 Qwen base models ($R^2 = 0.46$); (5)~\textbf{Token-Level Spectral Cascade} -- per-token alpha tracking reveals local synchronization that decays exponentially with layer distance, and is weaker for reasoning than factual tasks; (6)~\textbf{Reasoning Step Spectral Punctuation} -- phase-transition signatures align with reasoning step boundaries; and (7)~\textbf{Spectral Correctness Prediction} -- spectral $α$ alone achieves AUC $= 1.000$ (Qwen2.5-7B, late layers) and mean AUC $= 0.893$ across 6 models in predicting correctness \emph{before} the final answer is generated. Together, these findings establish a comprehensive \emph{spectral theory of reasoning} in transformers, revealing that the geometry of thought is universal in direction, architecture-specific in dynamics, and predictive of outcome.

Related papers

• Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability [51.56484100374058]
  We prove the first identifiability theorem for a mechanistic-interpretability primitive.<n>The spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.
  arXiv  Detail & Related papers  (2026-08-10T19:42:01Z)
• The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations [50.43168858368539]
  Large language models confidently produce outdated answers, and no existing method can detect them.<n>We show this is not an engineering failure but a structural one: temporal drift is encoded as a direction in the residual stream geometrically to both correctness and uncertainty.
  arXiv  Detail & Related papers  (2026-05-09T22:27:31Z)
• Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations [0.0]
  We find anti-concentration is observed in residual-stream difference-of-means vectors across five architecture families.<n>Results suggest transformers may rotate semantic content into spectrally quiet regions during contextualized processing.
  arXiv  Detail & Related papers  (2026-05-02T21:20:55Z)
• Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension [13.891522069967507]
  Spiking transformers achieve competitive accuracy with conventional transformers while offering $38$-$57times$ energy efficiency on neuromorphic hardware.<n>This paper establishes the first comprehensive expressivity theory for spiking self-attention.
  arXiv  Detail & Related papers  (2026-04-17T07:15:53Z)
• The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training [0.0]
  We show that phase transitions in neural network training are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates.<n>Adiabatic parameter $mathcalA = |G|_F / (, g2)$ controls circuit stability: $mathcalA ll 1$ (plateau), $mathcalA sim 1$ (phase transition), $mathcalA gg 1$ (forgetting)
  arXiv  Detail & Related papers  (2026-03-30T20:10:22Z)
• Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales [0.0]
  We show that transformer training trajectories evolve within only a few coherent directions.<n>In companion work, the same spectral geometry provides early-warning signals of grokking.
  arXiv  Detail & Related papers  (2026-03-14T04:46:05Z)
• Versor: A Geometric Sequence Architecture [0.0954904463032233]
  A novel sequence architecture design is introduced, Versor, which uses Conformal Geometric Algebra (CGA) in place of the traditional fundamental non-linear operations.<n>Versor is validated on chaotic N-body dynamics, topological reasoning, and standard multimodal benchmarks.
  arXiv  Detail & Related papers  (2026-02-10T19:00:02Z)
• Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds [0.5729426778193398]
  We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens.<n>We formalize the forward pass as a discrete coarse-graining map and relate the appearance of stable "concept basins" to fixed points of this renormalization-like dynamics.<n>The resulting low-entropy regime is characterized by a spectral tail collapse and by the formation of transient, reusable object-like structures in representation space.
  arXiv  Detail & Related papers  (2026-01-16T23:11:02Z)
• Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward [67.00373428443879]
  We introduce a paradigm shift towards subgoal-level evaluation and learning.<n>We first construct GeoGoal, a benchmark synthesized via a rigorous formal verification data engine.<n>We propose the Sub-Goal Verifiable Reward (SGVR) framework, which replaces sparse signals with dense rewards based on the Skeleton Rate.
  arXiv  Detail & Related papers  (2026-01-08T16:17:56Z)
• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space [56.37266873329401]
  Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density.<n>We propose $textbfDynamic Large Concept Models (DLCM)$, a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts from tokens to a compressed concept space where reasoning is more efficient.
  arXiv  Detail & Related papers  (2025-12-31T04:19:33Z)
• UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model [62.66515621965686]
  We introduce a novel theoretical framework with a Dual Discrete Diffusion (D3Diff) loss, unifying masked generative models with discrete score matching diffusion.<n>This D3Diff significantly enhances the model's ability to synthesize high-fidelity facial details aligned with text input.<n>We construct UniF$2$aceD-1M, a large-scale dataset comprising 130K fine-grained image-caption pairs and 1M visual question-answering pairs.
  arXiv  Detail & Related papers  (2025-03-11T07:34:59Z)
• 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)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• 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.