Skip to content

Formal Properties of Language as Constraints on Neural Dynamics

Sep 2026 · arXiv.org · Vol abs/2609.14384 · 0 citations
Computer Science

TL;DR

It is shown that algebraic properties of language specify invariants that mechanisms must preserve: non-associative hierarchical grouping, commutativity, recursive closure, recursive closure, access to substructures, and structured workspace transitions.

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.

View source

Similar papers

Aug 2026

Necessity and plurality of neural dynamics under ROSE

It is clarified that ROSE is an architecture for implementing hierarchical syntactic computation, bringing with it no commitment that its full code is obligatory for every act of meaning construction.

Elliot Murphy · 0 citations

The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning

STRAT is introduced, which partitions the residual stream into orthogonal Data and Type subspaces and uses Type-based attention and gating to govern Data transformations and in arithmetic, STRAT reduces median OOD error 35-fold relative to a Transformer baseline.

Cristina V. Lopes, Yuan-Gang Li, Justin Tian Jin Chen et al. · 0 citations
#artificial intelligence Preprint Sep 2026

REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs

Adding an auxiliary supervised contrastive (InfoNCE) loss during world-model warmup substantially improves sleep-phase clustering, and adding an auxiliary supervised contrastive loss during world-model warmup substantially improves sleep-phase clustering on LIBERO.

Riyaaz Shaik, Chandru Venkataraman · 0 citations

Grammatical "grandmother neurons" are rare in LLMs

Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or"probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds...

Lin-Yang He, N. Mesgarani · 0 citations

Signatures of semantic search in the activations of large language models

When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise their output into clusters of related items (e.g., sea animals) that are punctuated by strategic switches between clusters. In humans, this pattern can be explained by a semanti...

Luke Leckie, Peter M. Todd, Jacob G. Foster · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.