Sequences of Logits Reveal the Low Rank Structure of Language Models

• URL: http://arxiv.org/abs/2510.24966v1
• Date: Tue, 28 Oct 2025 20:55:58 GMT
• Title: Sequences of Logits Reveal the Low Rank Structure of Language Models
• Authors: Noah Golowich, Allen Liu, Abhishek Shetty,
• Abstract summary: We introduce an approach to study the low-dimensional structure of language models at a model-agnostic level.<n>We first empirically demonstrate that a wide range of modern language models exhibit low-rank structure.<n>We then show that this low-rank structure can be leveraged for generation.
• Score: 22.148282143726835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A major problem in the study of large language models is to understand their inherent low-dimensional structure. We introduce an approach to study the low-dimensional structure of language models at a model-agnostic level: as sequential probabilistic models. We first empirically demonstrate that a wide range of modern language models exhibit low-rank structure: in particular, matrices built from the model's logits for varying sets of prompts and responses have low approximate rank. We then show that this low-rank structure can be leveraged for generation -- in particular, we can generate a response to a target prompt using a linear combination of the model's outputs on unrelated, or even nonsensical prompts. On the theoretical front, we observe that studying the approximate rank of language models in the sense discussed above yields a simple universal abstraction whose theoretical predictions parallel our experiments. We then analyze the representation power of the abstraction and give provable learning guarantees.

Related papers

• Unraveling Syntax: How Language Models Learn Context-Free Grammars [1.0465074236788003]
  We study the learning dynamics of small models trained on synthetic languages generated from context-free grammars.<n>We find that unlike children, who first master simple substructures before progressing to more complex constructions, transformers reduce loss across all subgrammars in parallel.
  arXiv  Detail & Related papers  (2025-10-02T19:52:19Z)
• A Markov Categorical Framework for Language Modeling [9.910562011343009]
  Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes their representations, and enables complex behaviors, remains elusive.<n>We introduce a new analytical framework that models the single-step generation process as a composition of information-processing stages using the language of Markov categories.<n>This work presents a powerful new lens for understanding how information flows through a model and how the training objective shapes its internal geometry.
  arXiv  Detail & Related papers  (2025-07-25T13:14:03Z)
• Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures [49.19753720526998]
  We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
  arXiv  Detail & Related papers  (2025-05-11T17:44:14Z)
• Hidden Holes: topological aspects of language models [1.1172147007388977]
  We study the evolution of topological structure in GPT based large language models across depth and time during training. We show that the latter exhibit more topological complexity, with a distinct pattern of changes common to all natural languages but absent from synthetically generated data.
  arXiv  Detail & Related papers  (2024-06-09T14:25:09Z)
• Slaves to the Law of Large Numbers: An Asymptotic Equipartition Property for Perplexity in Generative Language Models [0.0]
  We show that the logarithmic perplexity of any large text generated by a language model must converge to the average entropy of its token distributions.<n>This defines a typical set'' that all long synthetic texts generated by a language model must belong to.
  arXiv  Detail & Related papers  (2024-05-22T16:23:40Z)
• On the Origins of Linear Representations in Large Language Models [51.88404605700344]
  We introduce a simple latent variable model to formalize the concept dynamics of the next token prediction. Experiments show that linear representations emerge when learning from data matching the latent variable model. We additionally confirm some predictions of the theory using the LLaMA-2 large language model.
  arXiv  Detail & Related papers  (2024-03-06T17:17:36Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge.<n>We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences.<n>We demonstrate that generative models like GPT can accurately learn and reason over CFG-defined hierarchies and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Language Model Cascades [72.18809575261498]
  Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. Cases with control flow and dynamic structure require techniques from probabilistic programming. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use.
  arXiv  Detail & Related papers  (2022-07-21T07:35:18Z)
• TAGPRIME: A Unified Framework for Relational Structure Extraction [71.88926365652034]
  TAGPRIME is a sequence tagging model that appends priming words about the information of the given condition to the input text. With the self-attention mechanism in pre-trained language models, the priming words make the output contextualized representations contain more information about the given condition. Extensive experiments and analyses on three different tasks that cover ten datasets across five different languages demonstrate the generality and effectiveness of TAGPRIME.
  arXiv  Detail & Related papers  (2022-05-25T08:57:46Z)
• Low-Rank Constraints for Fast Inference in Structured Models [110.38427965904266]
  This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. Experiments with neural parameterized structured models for language modeling, polyphonic music modeling, unsupervised grammar induction, and video modeling show that our approach matches the accuracy of standard models at large state spaces.
  arXiv  Detail & Related papers  (2022-01-08T00:47:50Z)
• Overestimation of Syntactic Representationin Neural Language Models [16.765097098482286]
  One popular method for determining a model's ability to induce syntactic structure trains a model on strings generated according to a template then tests the model's ability to distinguish such strings from superficially similar ones with different syntax. We illustrate a fundamental problem with this approach by reproducing positive results from a recent paper with two non-syntactic baseline language models.
  arXiv  Detail & Related papers  (2020-04-10T15:13:03Z)

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.