# What Do Language Models Learn in Context? The Structured Task Hypothesis

arXiv: https://arxiv.org/abs/2406.04216 · HTML: https://mlsanity.com/paper/2406.04216/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression](https://mlsanity.com/paper/2306.15063/) (2023)
- [The Learnability of In-Context Learning](https://mlsanity.com/paper/2303.07895/) (2023)
- [In-Context Language Learning: Architectures and Algorithms](https://mlsanity.com/paper/2401.12973/) (2024)
- [A Theory of Emergent In-Context Learning as Implicit Structure Induction](https://mlsanity.com/paper/2303.07971/) (2023)
- [The Transient Nature of Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2311.08360/) (2023)
- [In-Context Learning Learns Label Relationships but Is Not Conventional Learning](https://mlsanity.com/paper/2307.12375/) (2023)
- [Do pretrained Transformers Learn In-Context by Gradient Descent?](https://mlsanity.com/paper/2310.08540/) (2023)

## Built on by (most cited first, 13 of 13)

- [LLMs Are In-Context Bandit Reinforcement Learners](https://mlsanity.com/paper/2410.05362/) (2024)
- [Training Language Models via Neural Cellular Automata](https://mlsanity.com/paper/2603.10055/) (2026)
- [Episodic memory in AI agents poses risks that should be studied and mitigated](https://mlsanity.com/paper/2501.11739/) (2025)
- [StreamAdapter: Efficient Test Time Adaptation from Contextual Streams](https://mlsanity.com/paper/2411.09289/) (2024)
- [Investigating the Zone of Proximal Development of Language Models for In-Context Learning](https://mlsanity.com/paper/2502.06990/) (2025)
- [Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study](https://mlsanity.com/paper/2406.14629/) (2024)
- [Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models](https://mlsanity.com/paper/2409.04318/) (2024)
- [StaICC: Standardized Evaluation for Classification Task in In-context Learning](https://mlsanity.com/paper/2501.15708/) (2025)
- [InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning](https://mlsanity.com/paper/2509.12263/) (2025)
- [Binary Autoencoder for Mechanistic Interpretability of Large Language Models](https://mlsanity.com/paper/2509.20997/) (2025)
- [Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch](https://mlsanity.com/paper/2607.03660/) (2026)
- [What Neuroscience Can Teach AI About Learning in Continuously Changing Environments](https://mlsanity.com/paper/2507.02103/) (2025)
- [Distributed Sparse Interventions in Language Models](https://mlsanity.com/paper/2607.07128/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit an intriguing ability to learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL). Understandably, a swath of research has been dedicated to uncovering the theories underpinning ICL. One popular hypothesis explains ICL by task selection. LLMs identify the task based on the demonstration and generalize it to the prompt. Another popular hypothesis is that ICL is a form of meta-learning, i.e., the models learn a learning algorithm at pre-training time and apply it to the demonstration. Finally, a third hypothesis argues that LLMs use the demonstration to select a composition of tasks learned during pre-training to perform ICL. In this paper, we empirically explore these three hypotheses that explain LLMs' ability to learn in context with a suite of experiments derived from common text classification tasks. We invalidate the first two hypotheses with counterexamples and provide evidence in support of the last hypothesis. Our results suggest an LLM could learn a novel task in context via composing tasks learned during pre-training.