On the Emergence of Induction Heads for In-Context Learning

• URL: http://arxiv.org/abs/2511.01033v1
• Date: Sun, 02 Nov 2025 18:12:06 GMT
• Title: On the Emergence of Induction Heads for In-Context Learning
• Authors: Tiberiu Musat, Tiago Pimentel, Lorenzo Noci, Alessandro Stolfo, Mrinmaya Sachan, Thomas Hofmann,
• Abstract summary: We study the emergence of induction heads, a previously identified mechanism in two-layer transformers.<n>We explain the origin of this structure using a minimal ICL task formulation and a modified transformer architecture.
• Score: 121.64612469118464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers have become the dominant architecture for natural language processing. Part of their success is owed to a remarkable capability known as in-context learning (ICL): they can acquire and apply novel associations solely from their input context, without any updates to their weights. In this work, we study the emergence of induction heads, a previously identified mechanism in two-layer transformers that is particularly important for in-context learning. We uncover a relatively simple and interpretable structure of the weight matrices implementing the induction head. We theoretically explain the origin of this structure using a minimal ICL task formulation and a modified transformer architecture. We give a formal proof that the training dynamics remain constrained to a 19-dimensional subspace of the parameter space. Empirically, we validate this constraint while observing that only 3 dimensions account for the emergence of an induction head. By further studying the training dynamics inside this 3-dimensional subspace, we find that the time until the emergence of an induction head follows a tight asymptotic bound that is quadratic in the input context length.

Related papers

• Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks [0.0]
  We investigate the structure of learning dynamics in transformer models through carefully controlled arithmetic tasks.<n>Our results suggest a unifying geometric framework for understanding transformer learning.
  arXiv  Detail & Related papers  (2026-02-11T03:57:46Z)
• Transformers learn factored representations [62.86679034549244]
  Transformers pretrained via next token prediction learn to factor their world into parts.<n>We formalize two representational hypotheses: (1) a representation in the product space of all factors, whose dimension grows exponentially with the number of parts.<n>We derive precise predictions about the geometric structure of activations for each, including the number of subspaces, their dimensionality, and the arrangement of context embeddings within them.<n>This provides a principled explanation for why transformers decompose the world into parts, and suggests that interpretable low dimensional structure may persist even in models trained on complex data.
  arXiv  Detail & Related papers  (2026-02-02T17:49:06Z)
• Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits [22.333229451408414]
  Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood.<n>Existing interpretability methods treat attention heads and multilayer perceptron layers (MLPs) as indivisible units, overlooking possibilities of functional substructure learned within them.<n>We introduce a more fine-grained perspective that decomposes these components into singular directions, revealing superposed and independent computations within a single head or mechanistic.
  arXiv  Detail & Related papers  (2025-11-25T12:59:15Z)
• Understanding the Staged Dynamics of Transformers in Learning Latent Structure [5.944972519558522]
  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.
  arXiv  Detail & Related papers  (2025-11-24T17:20:42Z)
• Memory Limitations of Prompt Tuning in Transformers [45.158621811869466]
  We show that the amount of information memorized by a transformer cannot scale faster than linearly with the prompt length.<n>We also present the first formal proof of a phenomenon empirically observed in large language models: performance degradation.<n>This finding offers a fundamental understanding of the intrinsic limitations of transformer architectures.
  arXiv  Detail & Related papers  (2025-08-30T09:08:00Z)
• What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains [64.31313691823088]
  In-context learning (ICL) is a capability of transformers, through which trained models learn to adapt to new tasks by leveraging information from the input context.<n>We show that a two-layer transformer with one head per layer can indeed represent any conditional k-gram.
  arXiv  Detail & Related papers  (2025-08-10T07:03:01Z)
• Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods [45.94152084965753]
  We establish a novel connection between the attention mechanism and classical kernel methods.<n>We derive generalization error bounds in terms of the prompt length and the number of training tasks.<n>Our result characterizes how the generalization error scales with the number of training tasks.
  arXiv  Detail & Related papers  (2025-06-12T17:56:26Z)
• Understanding In-context Learning of Addition via Activation Subspaces [73.8295576941241]
  We study a structured family of few-shot learning tasks for which the true prediction rule is to add an integer $k$ to the input.<n>We then perform an in-depth analysis of individual heads, via dimensionality reduction and decomposition.<n>Our results demonstrate how tracking low-dimensional subspaces of localized heads across a forward pass can provide insight into fine-grained computational structures in language models.
  arXiv  Detail & Related papers  (2025-05-08T11:32:46Z)
• Rethinking Associative Memory Mechanism in Induction Head [37.93644115914534]
  This paper investigates how a two-layer transformer thoroughly captures in-context information and balances it with pretrained bigram knowledge in next token prediction.<n>We theoretically analyze the representation of weight matrices in attention layers and the resulting logits when a transformer is given prompts generated by a bigram model.
  arXiv  Detail & Related papers  (2024-12-16T05:33:05Z)
• 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)
• What is Intelligence? A Cycle Closure Perspective [6.0044467881527614]
  We argue for a structural-dynamical account rooted in a topological closure law.<n>We show that textbfMemory-Amortized Inference (MAI) is the computational mechanism that implements SbS,$rightarrow$,CCUP through dual bootstrapping.
  arXiv  Detail & Related papers  (2024-04-08T13:06:23Z)
• How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations [98.7450564309923]
  This paper takes initial steps on understanding in-context learning (ICL) in more complex scenarios, by studying learning with representations. We construct synthetic in-context learning problems with a compositional structure, where the label depends on the input through a possibly complex but fixed representation function. We show theoretically the existence of transformers that approximately implement such algorithms with mild depth and size.
  arXiv  Detail & Related papers  (2023-10-16T17:40:49Z)

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.