Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models

• URL: http://arxiv.org/abs/2601.11622v1
• Date: Sun, 11 Jan 2026 21:57:52 GMT
• Title: Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models
• Authors: Hassan Ugail, Newton Howard,
• Abstract summary: Large language models perform text generation through high-dimensional internal dynamics.<n>Most interpretability approaches emphasise static representations or causal interventions, leaving temporal structure largely unexplored.<n>We discuss a composite dynamical metric, computed from activation time-series during autoregressive generation.
• Score: 0.8694591156258423
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models perform text generation through high-dimensional internal dynamics, yet the temporal organisation of these dynamics remains poorly understood. Most interpretability approaches emphasise static representations or causal interventions, leaving temporal structure largely unexplored. Drawing on neuroscience, where temporal integration and metastability are core markers of neural organisation, we adapt these concepts to transformer models and discuss a composite dynamical metric, computed from activation time-series during autoregressive generation. We evaluate this metric in GPT-2-medium across five conditions: structured reasoning, forced repetition, high-temperature noisy sampling, attention-head pruning, and weight-noise injection. Structured reasoning consistently exhibits elevated metric relative to repetitive, noisy, and perturbed regimes, with statistically significant differences confirmed by one-way ANOVA and large effect sizes in key comparisons. These results are robust to layer selection, channel subsampling, and random seeds. Our findings demonstrate that neuroscience-inspired dynamical metrics can reliably characterise differences in computational organisation across functional regimes in large language models. We stress that the proposed metric captures formal dynamical properties and does not imply subjective experience.

Related papers

• Scale-Dependent Semantic Dynamics Revealed by Allan Deviation [0.0]
  We analyze the stability of meaning by treating ordered sentence embeddings as a displacement signal.<n>We find that while large language models successfully mimic the local scaling statistics of human text, they exhibit a systematic reduction in their stability horizon.
  arXiv  Detail & Related papers  (2026-01-29T13:10:59Z)
• Transformer Learning of Chaotic Collective Dynamics in Many-Body Systems [0.0]
  We show that a self-attention-based transformer framework provides an effective approach for modeling chaotic collective dynamics.<n>We study the one-dimensional semiclassical Holstein model, where interaction quenches induce strongly nonlinear and chaotic dynamics.<n>Our results establish self-attention as a powerful mechanism for learning effective reduced dynamics in chaotic many-body systems.
  arXiv  Detail & Related papers  (2026-01-27T01:33:33Z)
• Temporal Complexity and Self-Organization in an Exponential Dense Associative Memory Model [0.0]
  Temporal Complexity (TC) is a framework that characterizes complex systems by intermittent transition events between order and disorder.<n>Our results reveal that the SEDAM model exhibits regimes of complex intermittency characterized by nontrivial temporal correlations and scale-free behavior.<n>This study highlights the relevance of TC as a complementary framework for understanding learning and information processing in artificial and biological neural systems.
  arXiv  Detail & Related papers  (2026-01-16T18:01:14Z)
• Causal Structure Learning for Dynamical Systems with Theoretical Score Analysis [7.847876045564289]
  Real world systems evolve in continuous-time according to their underlying causal relationships, yet their dynamics are often unknown.<n>We propose CaDyT, a novel method for causal discovery on dynamical systems.<n>Our experiments show that CaDyT outperforms state-of-the-art methods on both regularly and irregularly-sampled data.
  arXiv  Detail & Related papers  (2025-12-16T12:41:22Z)
• Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation [46.40087254928057]
  We present SPARK, a physics-guided quantitative augmentation plugin.<n>Experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-28T09:30:35Z)
• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Allostatic Control of Persistent States in Spiking Neural Networks for perception and computation [79.16635054977068]
  We introduce a novel model for updating perceptual beliefs about the environment by extending the concept of Allostasis to the control of internal representations.<n>In this paper, we focus on an application in numerical cognition, where a bump of activity in an attractor network is used as a spatial numerical representation.
  arXiv  Detail & Related papers  (2025-03-20T12:28:08Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes.<n>Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• Neural Persistence Dynamics [8.197801260302642]
  We consider the problem of learning the dynamics in the topology of time-evolving point clouds. Our proposed model - $textitNeural Persistence Dynamics$ - substantially outperforms the state-of-the-art across a diverse set of parameter regression tasks.
  arXiv  Detail & Related papers  (2024-05-24T17:20:18Z)
• Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics [6.829711787905569]
  We propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data. Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time. In both continuous-time and discrete-time instructional examples we demonstrate that our model can well approximate the original system.
  arXiv  Detail & Related papers  (2022-06-07T02:25:38Z)
• Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation [54.864148836486166]
  We propose to incorporate the explicit syntactic and semantic structures of languages into a non-autoregressive Transformer. Our model achieves a significantly faster speed, as well as keeps the translation quality when compared with several state-of-the-art non-autoregressive models.
  arXiv  Detail & Related papers  (2021-01-22T04:12:17Z)

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.