Formal Properties of Language as Constraints on Neural Dynamics

• URL: http://arxiv.org/abs/2609.14384v1
• Date: Sun, 13 Sep 2026 08:41:56 GMT
• Title: Formal Properties of Language as Constraints on Neural Dynamics
• Abstract summary: Current research annotates stimuli with linguistic variables and tests which saturate electrodes, voxels, or language-model layers predict neural activity.<n>Here, we show that algebraic properties of language specify invariants that mechanisms must preserve.<n>We propose a novel neural binding operation we term 'Meld': two constituent populations converge through shared synapses, integrate sublinearly, and Merge.
• Score: 0.20305676256390937
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: What must a neural system be capable of to implement language? Current research annotates stimuli with linguistic variables and tests which electrodes, voxels, or language-model layers predict neural activity. Yet predictive success leaves mechanisms under-constrained. Here, we show that algebraic properties of language specify invariants that mechanisms must preserve: non-associative hierarchical grouping, commutativity, recursive closure, access to substructures, and structured workspace transitions. We term this the Neural Admissibility Program (NAP). Syntactic structure building is analyzed algebraically, with candidate mechanisms offered for each requirement: content-addressable workspace memory, graph-structured transient dynamics scheduling structure-building operations (e.g. stable heteroclinic channels), and a phase-coupled sealing operation recording grouping. Simulations show that a corrected Marcolli-Berwick entropy-optimized binding gate preserves grouping only within a narrow commitment band. As an alternative, we propose a novel neural binding operation we term 'Meld': two constituent populations converge through shared synapses, integrate sublinearly, and saturate. Meld is, to our knowledge, the closest neurally plausible composition law to syntactic Merge. It preserves every NAP invariant, uses known cortical operations, and recovers hierarchical structure at every tested depth and temperature. It predicts that effective population dimensionality separates alternative bracketings and that the composite depends on constituent disagreement. Importantly, the laws decoding bracketing most accurately are a priori inadmissible, showing that decoding accuracy alone cannot adjudicate between mechanisms. By specifying how neural dynamics can remain faithful to linguistic structure, the NAP changes the criterion by which neural implementations of cognition are evaluated.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences [89.71422932447423]
  LOGOS is a scientific generative language model that unifies heterogeneous tasks across the natural sciences.<n>By representing spatial contact and constraint patterns as discrete tokens, the model captures complex structural interactions in a purely sequential manner.<n>Across diverse tasks, LOGOS consistently matches or outperforms domain-specific baselines.
  arXiv  Detail & Related papers  (2026-06-15T16:14:53Z)
• The Sensation Modulating Network:Haltability as the architectural ground for object-directed phenomenology [0.0]
  We argue the impasse stems from an incomplete account of the embodied agent's architecture.<n>We propose the Sensation Modulating Network (SMN), the cognitive agent conceived as the whole body.<n>The SMN reconciles the cognitivism-4E debate: recursion lives in the modifiable dynamics of Negotiable Action Patterns.
  arXiv  Detail & Related papers  (2026-05-26T11:15:56Z)
• Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language [0.0]
  Language models are typically trained to predict the next token in a sequence.<n>Here, we explore an alternative predictive principle from reinforcement learning: Successor Representations.<n>We train neural networks to predict future word distributions across multiple temporal horizons.
  arXiv  Detail & Related papers  (2026-05-23T13:55:09Z)
• Separable neural architectures as a primitive for unified predictive and generative intelligence [0.7318787399845128]
  We formalise a representational class that unifies additive, quadratic and tensor-decomposed neural models.<n>SNAs impose a structural inductive bias that factorises high-dimensional mappings into low-composed components.<n>These results establish the separable neural architecture as the domain-agnostic primitive for predictive and generative intelligence.
  arXiv  Detail & Related papers  (2026-03-12T17:56:54Z)
• Objective-Free Local Learning and Emergent Language Structure in Thinking Machines [0.0]
  We present a neuro-symbolic framework for generative language modeling based on local, event-driven emergent learning.<n>At its core is a hierarchical Hopfield memory chain acting as a compositional short-term memory and dynamic tokenizer.<n>We demonstrate that briefly activating a new neuron during inference binds distributed multi-scale token features into a symbolic embedding.
  arXiv  Detail & Related papers  (2025-06-29T15:29:13Z)
• 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)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• ROSE: A Neurocomputational Architecture for Syntax [0.0]
  This article proposes a neurocomputational architecture for syntax, termed the ROSE model. Under ROSE, the basic data structures of syntax are atomic features, types of mental representations (R), and are coded at the single-unit and ensemble level. Distinct forms of low frequency coupling and phase-amplitude coupling (delta-theta coupling via pSTS-IFG; theta-gamma coupling via IFG to conceptual hubs) then encode these structures onto distinct workspaces (E)
  arXiv  Detail & Related papers  (2023-03-15T18:44:37Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Equivariant Transduction through Invariant Alignment [71.45263447328374]
  We introduce a novel group-equivariant architecture that incorporates a group-in hard alignment mechanism. We find that our network's structure allows it to develop stronger equivariant properties than existing group-equivariant approaches. We additionally find that it outperforms previous group-equivariant networks empirically on the SCAN task.
  arXiv  Detail & Related papers  (2022-09-22T11:19:45Z)

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.