A Markov Categorical Framework for Language Modeling

• URL: http://arxiv.org/abs/2507.19247v1
• Date: Fri, 25 Jul 2025 13:14:03 GMT
• Title: A Markov Categorical Framework for Language Modeling
• Authors: Yifan Zhang,
• Abstract summary: Auto-regressive language models factorize sequence probabilities and are trained by minimizing the negative log-likelihood (NLL) objective.<n>This work introduces a unifying analytical framework using Markov Categories (MCs) to deconstruct the AR generation process and the NLL objective.<n>By analyzing the information geometry of the model's prediction head, we show that NLL implicitly forces the learned representation space to align with the eigenspectrum of a similarity predictive operator.
• Score: 5.980612601840882
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Auto-regressive language models factorize sequence probabilities and are trained by minimizing the negative log-likelihood (NLL) objective. While empirically powerful, a deep theoretical understanding of why this simple objective yields such versatile representations remains elusive. This work introduces a unifying analytical framework using Markov Categories (MCs) to deconstruct the AR generation process and the NLL objective. We model the single-step generation map as a composition of Markov kernels in the category Stoch. This compositional view, when enriched with statistical divergences, allows us to dissect information flow and learned geometry. Our framework makes three main contributions. First, we provide a formal, information-theoretic rationale for the success of modern speculative decoding methods like EAGLE, quantifying the information surplus in hidden states that these methods exploit. Second, we formalize how NLL minimization forces the model to learn not just the next token, but the data's intrinsic conditional stochasticity, a process we analyze using categorical entropy. Third, and most centrally, we prove that NLL training acts as an implicit form of spectral contrastive learning. By analyzing the information geometry of the model's prediction head, we show that NLL implicitly forces the learned representation space to align with the eigenspectrum of a predictive similarity operator, thereby learning a geometrically structured space without explicit contrastive pairs. This compositional and information-geometric perspective reveals the deep structural principles underlying the effectiveness of modern LMs. Project Page: https://github.com/asiresearch/lm-theory

Related papers

• Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation [4.480310276450028]
  We propose a training strategy for a 3D LiDAR semantic segmentation model that learns structural relationships between classes through abstraction. This is achieved by implicitly modeling these relationships using a learning rule for hierarchical multi-label classification (HMC) Our detailed analysis demonstrates that this training strategy not only improves the model's confidence calibration but also retains additional information useful for downstream tasks such as fusion, prediction, and planning.
  arXiv  Detail & Related papers  (2024-04-09T08:49:01Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• Surprisal Driven $k$-NN for Robust and Interpretable Nonparametric Learning [1.4293924404819704]
  We shed new light on the traditional nearest neighbors algorithm from the perspective of information theory. We propose a robust and interpretable framework for tasks such as classification, regression, density estimation, and anomaly detection using a single model. Our work showcases the architecture's versatility by achieving state-of-the-art results in classification and anomaly detection.
  arXiv  Detail & Related papers  (2023-11-17T00:35:38Z)
• Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals [67.64770842323966]
  Causal explanations of predictions of NLP systems are essential to ensure safety and establish trust. Existing methods often fall short of explaining model predictions effectively or efficiently. We propose two approaches for counterfactual (CF) approximation.
  arXiv  Detail & Related papers  (2023-10-01T07:31:04Z)
• Evaluating and Explaining Large Language Models for Code Using Syntactic Structures [74.93762031957883]
  This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code. At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes. We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
  arXiv  Detail & Related papers  (2023-08-07T18:50:57Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Learning with Explanation Constraints [91.23736536228485]
  We provide a learning theoretic framework to analyze how explanations can improve the learning of our models. We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.
  arXiv  Detail & Related papers  (2023-03-25T15:06:47Z)
• Principled and Efficient Motif Finding for Structure Learning of Lifted Graphical Models [5.317624228510748]
  Structure learning is a core problem in AI central to the fields of neuro-symbolic AI and statistical relational learning. We present the first principled approach for mining structural motifs in lifted graphical models. We show that we outperform state-of-the-art structure learning approaches by up to 6% in terms of accuracy and up to 80% in terms of runtime.
  arXiv  Detail & Related papers  (2023-02-09T12:21:55Z)
• Experimental Observations of the Topology of Convolutional Neural Network Activations [2.4235626091331737]
  Topological data analysis provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification.
  arXiv  Detail & Related papers  (2022-12-01T02:05:44Z)
• Layer-wise Analysis of a Self-supervised Speech Representation Model [26.727775920272205]
  Self-supervised learning approaches have been successful for pre-training speech representation models. Not much has been studied about the type or extent of information encoded in the pre-trained representations themselves.
  arXiv  Detail & Related papers  (2021-07-10T02:13:25Z)
• From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [99.44881722969046]
  We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. We optimize an innovative feature-level objective inspired by classical Canonical Correlation Analysis. Our method performs competitively on seven public graph datasets.
  arXiv  Detail & Related papers  (2021-06-23T15:55:47Z)
• Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning [20.506232306308977]
  Latent structure models are a powerful tool for modeling language data. One challenge with end-to-end training of these models is the argmax operation, which has null gradient. We explore latent structure learning through the angle of pulling back the downstream learning objective.
  arXiv  Detail & Related papers  (2020-10-05T21:56:00Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)

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.