# Understanding In-Context Learning from Repetitions

arXiv: https://arxiv.org/abs/2310.00297 · HTML: https://mlsanity.com/paper/2310.00297/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 30 Sep 2023.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [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)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [Transformers as Algorithms: Generalization and Stability in In-context Learning](https://mlsanity.com/paper/2301.07067/) (2023)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations](https://mlsanity.com/paper/2205.12685/) (2022)

## Built on by (most cited first, 29 of 29)

- [OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs](https://mlsanity.com/paper/2504.04030/) (2025)
- [WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning](https://mlsanity.com/paper/2312.14187/) (2023)
- [The broader spectrum of in-context learning](https://mlsanity.com/paper/2412.03782/) (2024)
- [Parallel Structures in Pre-training Data Yield In-Context Learning](https://mlsanity.com/paper/2402.12530/) (2024)
- [Repetition Neurons: How Do Language Models Produce Repetitions?](https://mlsanity.com/paper/2410.13497/) (2024)
- [S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency](https://mlsanity.com/paper/2502.04790/) (2025)
- [Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression](https://mlsanity.com/paper/2404.00489/) (2024)
- [FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights](https://mlsanity.com/paper/2602.02905/) (2026)
- [Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing](https://mlsanity.com/paper/2502.15208/) (2025)
- [Enhancing Latent Computation in Transformers with Latent Tokens](https://mlsanity.com/paper/2505.12629/) (2025)
- [CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing](https://mlsanity.com/paper/2410.16670/) (2024)
- [RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models](https://mlsanity.com/paper/2402.13463/) (2024)
- [Repetitions are not all alike: distinct mechanisms sustain repetition in language models](https://mlsanity.com/paper/2504.01100/) (2025)
- [Counterfactual Trace Auditing of LLM Agent Skills](https://mlsanity.com/paper/2605.11946/) (2026)
- [Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning](https://mlsanity.com/paper/2406.11890/) (2024)
- [ELICIT: LLM Augmentation via External In-Context Capability](https://mlsanity.com/paper/2410.09343/) (2024)
- [Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning](https://mlsanity.com/paper/2507.07810/) (2025)
- [From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When](https://mlsanity.com/paper/2406.00131/) (2024)
- [Task Schema and Binding: A Double Dissociation Study of In-Context Learning](https://mlsanity.com/paper/2512.17325/) (2025)
- [Identifying and Analyzing Performance-Critical Tokens in Large Language Models](https://mlsanity.com/paper/2401.11323/) (2024)
- [From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set](https://mlsanity.com/paper/2411.15387/) (2024)
- [Review of Hallucination Understanding in Large Language and Vision Models](https://mlsanity.com/paper/2510.00034/) (2025)
- [Crafting a Good Prompt or Providing Exemplary Dialogues? A Study of In-Context Learning for Persona-based Dialogue Generation](https://mlsanity.com/paper/2402.09954/) (2024)
- [Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning](https://mlsanity.com/paper/2601.07903/) (2026)
- [Composited-Nested-Learning with Data Augmentation for Nested Named Entity Recognition](https://mlsanity.com/paper/2406.12779/) (2024)
- [LiFT: How to Enable In-Context Learning for Longitudinal Modelling](https://mlsanity.com/paper/2604.16382/) (2026)
- [Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation](https://mlsanity.com/paper/2609.04484/) (2026)
- [Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective](https://mlsanity.com/paper/2610.03185/) (2026)
- [Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence](https://mlsanity.com/paper/2610.04791/) (2026)

## Abstract (arXiv)

This paper explores the elusive mechanism underpinning in-context learning in Large Language Models (LLMs). Our work provides a novel perspective by examining in-context learning via the lens of surface repetitions. We quantitatively investigate the role of surface features in text generation, and empirically establish the existence of token co-occurrence reinforcement, a principle that strengthens the relationship between two tokens based on their contextual co-occurrences. By investigating the dual impacts of these features, our research illuminates the internal workings of in-context learning and expounds on the reasons for its failures. This paper provides an essential contribution to the understanding of in-context learning and its potential limitations, providing a fresh perspective on this exciting capability.