The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers

• URL: http://arxiv.org/abs/2608.25166v1
• Date: Tue, 25 Aug 2026 21:27:21 GMT
• Title: The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers
• Abstract summary: We ask whether the grammatical role of tokens, as marked by their part-of-speech (PoS) tag, shapes the local geometry of this manifold.<n>We show that geometric features alone recover a token's grammatical role, and use them to interpret how the semantic content of each PoS evolves across layers in a downstream classification task.
• Score: 6.995112644485604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such data tend to concentrate on lower-dimensional sub-manifolds, a form of compression quantified by the Intrinsic Dimensionality (ID), the minimum number of independent variables needed to represent them without significant information loss. In this work, we ask whether the grammatical role of tokens, as marked by their part-of-speech (PoS) tag, shapes the local geometry of this manifold. To this end: (1) We investigate the layer-wise evolution of ID, finding that closed-class items expand earlier and collapse sooner than open-class ones; (2) We show its expansion and contraction to be explained by changes in the neighborhood structure, and hence in the relations between words within a sentence; (3) We compare encoders (ModernBERT, bigbird-roberta-large) and decoders (gemma-2-2B, Llama-3.2-3B), finding that the two families evolve differently across layers, consistently with how each integrates context;(4) We show that geometric features alone recover a token's grammatical role, and use them to interpret how the semantic content of each PoS evolves across layers in a downstream classification task.

Related papers

• Decomposing how prompting steers behavior [0.0]
  We decompose prompt-induced representational change into interpretable geometric components.<n>Our framework reveals how models route task-relevant structure to produce prompt-driven behavior.
  arXiv  Detail & Related papers  (2026-06-02T03:27:24Z)
• OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention [80.51557267896938]
  We present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting.<n>At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance.<n>To further enforce object-level semantic consistency, we introduce a structured codebook that serves as a set of shared semantic primitives.
  arXiv  Detail & Related papers  (2026-05-07T12:10:07Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models [2.3204178451683264]
  We introduce Rotor-Invariant Shift Estimation (RISE), a geometric approach that represents semantic transformations as consistent rotational operations in embedding space.<n>RISE operations have the ability to operate across both languages and models with high transfer of performance.<n>This work provides the first systematic demonstration that discourse-level semantic transformations correspond to consistent geometric operations in multilingual embedding spaces.
  arXiv  Detail & Related papers  (2025-10-10T18:51:32Z)
• Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction [61.484280369655536]
  Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations.<n>Existing SOP methods typically aggregate contextual features to assist the occupancy representation learning.<n>We introduce a new Hierarchical context alignment paradigm for a more accurate SOP (Hi-SOP)
  arXiv  Detail & Related papers  (2024-12-11T09:53:10Z)
• Semantic Cells: Evolutional Process to Acquire Sense Diversity of Items [0.0]
  Author presents a method in which a word or item embraces multiple semantic vectors that evolve via interaction with others. We obtained two preliminary results: the role of a word that evolves to acquire the largest or lower-middle variance of semantic vectors tends to be explainable. The epicenters of earthquakes that acquire larger variance via crossover, corresponding to the interaction with diverse areas of land crust, are likely to correspond to the epicenters of forthcoming large earthquakes.
  arXiv  Detail & Related papers  (2024-04-23T05:11:08Z)
• The geometry of hidden representations of large transformer models [43.16765170255552]
  Large transformers are powerful architectures used for self-supervised data analysis across various data types. We show that the semantic structure of the dataset emerges from a sequence of transformations between one representation and the next. We show that the semantic information of the dataset is better expressed at the end of the first peak, and this phenomenon can be observed across many models trained on diverse datasets.
  arXiv  Detail & Related papers  (2023-02-01T07:50:26Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions [7.615096161060399]
  We investigate a context-aware and dictionary-free mapping approach by leveraging parallel corpora. Our findings unfold the tight relationship between isotropy, isometry, and isomorphism in normalized contextual embedding spaces.
  arXiv  Detail & Related papers  (2021-07-19T22:57:36Z)
• Unsupervised Distillation of Syntactic Information from Contextualized Word Representations [62.230491683411536]
  We tackle the task of unsupervised disentanglement between semantics and structure in neural language representations. To this end, we automatically generate groups of sentences which are structurally similar but semantically different. We demonstrate that our transformation clusters vectors in space by structural properties, rather than by lexical semantics.
  arXiv  Detail & Related papers  (2020-10-11T15:13:18Z)

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.