Understanding the Staged Dynamics of Transformers in Learning Latent Structure

• URL: http://arxiv.org/abs/2511.19328v1
• Date: Mon, 24 Nov 2025 17:20:42 GMT
• Title: Understanding the Staged Dynamics of Transformers in Learning Latent Structure
• Authors: Rohan Saha, Farzane Aminmansour, Alona Fyshe,
• Abstract summary: We train a small decoder-only transformer on three task variants.<n>We show that the model acquires capabilities in discrete stages.<n>We also identify a crucial asymmetry, where the model can compose fundamental rules robustly, but struggles to decompose complex examples to discover the fundamental rules.
• Score: 5.944972519558522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While transformers can discover latent structure from context, the dynamics of how they acquire different components of the latent structure remain poorly understood. In this work, we use the Alchemy benchmark, to investigate the dynamics of latent structure learning. We train a small decoder-only transformer on three task variants: 1) inferring missing rules from partial contextual information, 2) composing simple rules to solve multi-step sequences, and 3) decomposing complex multi-step examples to infer intermediate steps. By factorizing each task into interpretable events, we show that the model acquires capabilities in discrete stages, first learning the coarse grained rules, before learning the complete latent structure. We also identify a crucial asymmetry, where the model can compose fundamental rules robustly, but struggles to decompose complex examples to discover the fundamental rules. These findings offer new insights into understanding how a transformer model learns latent structures, providing a granular view of how these capabilities evolve during training.

Related papers

• Incremental Learning of Sparse Attention Patterns in Transformers [29.54151079577767]
  This paper introduces a high-order Markov chain task to investigate how transformers learn to integrate information from multiple past positions.<n>We identify a shift in learning dynamics from competitive, where heads converge on the most statistically dominant pattern, to cooperative, where heads specialize in distinct patterns.
  arXiv  Detail & Related papers  (2026-02-22T12:16:06Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers [18.662154648423087]
  This paper theoretically demonstrates how the two-stage training dynamics potentially occur in transformers.<n>To our best knowledge, this is the first rigorous result regarding a feature-level two-stage optimization process in transformers.
  arXiv  Detail & Related papers  (2025-02-28T03:27:24Z)
• Structure Development in List-Sorting Transformers [0.0]
  We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers.<n>At the end of training, the model organizes its attention heads in two main modes that we refer to as vocabulary-splitting and copy-suppression.
  arXiv  Detail & Related papers  (2025-01-30T15:56:25Z)
• Interpreting Affine Recurrence Learning in GPT-style Transformers [54.01174470722201]
  In-context learning allows GPT-style transformers to generalize during inference without modifying their weights. This paper focuses specifically on their ability to learn and predict affine recurrences as an ICL task. We analyze the model's internal operations using both empirical and theoretical approaches.
  arXiv  Detail & Related papers  (2024-10-22T21:30:01Z)
• In-Context Learning with Representations: Contextual Generalization of Trained Transformers [66.78052387054593]
  In-context learning (ICL) refers to a capability of pretrained large language models, which can learn a new task given a few examples during inference. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks.
  arXiv  Detail & Related papers  (2024-08-19T16:47:46Z)
• Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers [16.26331213222281]
  We analyze the solutions simple transformer blocks implement when tackling the histogram task.<n>This task reveals a complex interplay between predictive performance, vocabulary and embedding sizes, token-mixing mechanisms, and feed-forward layer capacity.
  arXiv  Detail & Related papers  (2024-07-16T09:48:10Z)
• Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations [75.14793516745374]
  We propose to strengthen the structural inductive bias of a Transformer by intermediate pre-training. Our experiments confirm that this helps with few-shot learning of syntactic tasks such as chunking. Our analysis shows that the intermediate pre-training leads to attention heads that keep track of which syntactic transformation needs to be applied to which token.
  arXiv  Detail & Related papers  (2024-07-05T14:29:44Z)
• Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing [10.206921909332006]
  Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate.<n>We discover that the parameter initialization scale plays a critical role in determining whether the model learns inferential (reasoning-based) solutions.<n>We further find that inferential (reasoning-based) solutions exhibit low complexity bias, which we hypothesize is a key factor enabling them to learn individual mappings for single anchors.
  arXiv  Detail & Related papers  (2024-05-08T20:23:24Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding [56.222097640468306]
  We provide mechanistic understanding of how transformers learn "semantic structure" We show, through a combination of mathematical analysis and experiments on Wikipedia data, that the embedding layer and the self-attention layer encode the topical structure.
  arXiv  Detail & Related papers  (2023-03-07T21:42:17Z)
• Unveiling Transformers with LEGO: a synthetic reasoning task [23.535488809197787]
  We study how the transformer architecture learns to follow a chain of reasoning. In some data regime the trained transformer finds "shortcut" solutions to follow the chain of reasoning. We find that one can prevent such shortcut with appropriate architecture modification or careful data preparation.
  arXiv  Detail & Related papers  (2022-06-09T06:30:17Z)

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.