Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations

• URL: http://arxiv.org/abs/2505.08348v2
• Date: Wed, 08 Oct 2025 06:08:10 GMT
• Title: Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations
• Authors: Yize Zhao, Christos Thrampoulidis,
• Abstract summary: Next-token prediction (NTP) optimization leads language models to extract and organize semantic structure from text.<n>We demonstrate that concepts corresponding to larger singular values are learned earlier during training, yielding a natural semantic hierarchy.<n>This insight motivates orthant-based clustering, a method that combines concept signs to identify interpretable semantic categories.
• Score: 34.88156871518115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate how next-token prediction (NTP) optimization leads language models to extract and organize semantic structure from text. Our analysis, based on a tractable mathematical model and controlled synthetic data, reveals that NTP implicitly guides models to factor a centered support matrix encoding context-to-next-token co-occurrence patterns via singular value decomposition (SVD). While models never explicitly construct this matrix, learned word and context embeddings converge to its SVD factors, with singular vectors encoding latent semantic concepts through their sign patterns. We demonstrate that concepts corresponding to larger singular values are learned earlier during training, yielding a natural semantic hierarchy where broad categories emerge before fine-grained ones. This insight motivates orthant-based clustering, a method that combines concept signs to identify interpretable semantic categories. We validate our findings on synthetic datasets and pretrained language models, recovering diverse semantic structures such as grammatical categories, named entity types, and topical distinctions (medical, entertainment). Our work bridges classical distributional semantics and neural collapse geometry, characterizing how gradient-based optimization implicitly determines both the matrix representation and factorization method that encode semantic structure.

Related papers

• Concept-Guided Interpretability via Neural Chunking [54.73787666584143]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract these emerging entities, complementing each other based on label availability and dimensionality.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning [31.632816425798108]
  Tokenization is a necessary component within the current architecture of many language models.<n>We discuss how tokens and pretraining can act as a backdoor for bias and other unwanted content.<n>We relay evidence that the tokenization algorithm's objective function impacts the large language model's cognition.
  arXiv  Detail & Related papers  (2024-12-14T18:18:52Z)
• A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs [50.982315553104975]
  Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms.<n>Most SMMs are manually built by human experts using bottom-up procedures.<n>We propose a novel graph-based algorithm that automatically generates conceptual spaces and SMMs in a top-down manner.
  arXiv  Detail & Related papers  (2024-12-02T12:06:41Z)
• Collapsed Language Models Promote Fairness [88.48232731113306]
  We find that debiased language models exhibit collapsed alignment between token representations and word embeddings.<n>We design a principled fine-tuning method that can effectively improve fairness in a wide range of debiasing methods.
  arXiv  Detail & Related papers  (2024-10-06T13:09:48Z)
• Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations [24.211603400355756]
  Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models.<n>We look at how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model representations.<n>We validate our findings on synthetic and small-scale real language datasets.
  arXiv  Detail & Related papers  (2024-08-27T21:46:47Z)
• The Foundations of Tokenization: Statistical and Computational Concerns [51.370165245628975]
  Tokenization is a critical step in the NLP pipeline.<n>Despite its recognized importance as a standard representation method in NLP, the theoretical underpinnings of tokenization are not yet fully understood.<n>The present paper contributes to addressing this theoretical gap by proposing a unified formal framework for representing and analyzing tokenizer models.
  arXiv  Detail & Related papers  (2024-07-16T11:12:28Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Contextual Dictionary Lookup for Knowledge Graph Completion [32.493168863565465]
  Knowledge graph completion (KGC) aims to solve the incompleteness of knowledge graphs (KGs) by predicting missing links from known triples. Most existing embedding models map each relation into a unique vector, overlooking the specific fine-grained semantics of them under different entities. We present a novel method utilizing contextual dictionary lookup, enabling conventional embedding models to learn fine-grained semantics of relations in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-06-13T12:13:41Z)
• Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling [0.0]
  The black-box structure of the deep neural network in pre-trained language models seriously limits the interpretability of the language modeling process. A Word-Context-Coupled Space (W2CSpace) is proposed by introducing the alignment processing between uninterpretable neural representation and interpretable statistical logic. Our language model can achieve better performance and highly credible interpretable ability compared to related state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-19T09:26:02Z)
• Linear Spaces of Meanings: Compositional Structures in Vision-Language Models [110.00434385712786]
  We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs) We first present a framework for understanding compositional structures from a geometric perspective. We then explain what these structures entail probabilistically in the case of VLM embeddings, providing intuitions for why they arise in practice.
  arXiv  Detail & Related papers  (2023-02-28T08:11:56Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Learning Disentangled Representations for Natural Language Definitions [0.0]
  We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences, for training a Variational Autoencoder to learn disentangled representations.
  arXiv  Detail & Related papers  (2022-09-22T14:31:55Z)
• Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis [13.07356367140208]
  We introduce DistNLI, a new diagnostic dataset for natural language inference. We find that the extent of models' understanding is associated with model size and vocabulary size.
  arXiv  Detail & Related papers  (2022-09-11T00:33:28Z)
• Pretraining on Interactions for Learning Grounded Affordance Representations [22.290431852705662]
  We train a neural network to predict objects' trajectories in a simulated interaction. We show that our network's latent representations differentiate between both observed and unobserved affordances. Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.
  arXiv  Detail & Related papers  (2022-07-05T19:19:53Z)
• Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification [68.06496970320595]
  Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. We present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs.
  arXiv  Detail & Related papers  (2022-05-18T07:47:01Z)
• A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
  We propose a novel latent-variable formulation for constructing intrinsic probes. We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
  arXiv  Detail & Related papers  (2022-01-20T15:01:12Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• Compositional Generalization via Semantic Tagging [81.24269148865555]
  We propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models. We show that the proposed approach consistently improves compositional generalization across model architectures, domains, and semantic formalisms.
  arXiv  Detail & Related papers  (2020-10-22T15:55:15Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)
• 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.