Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Niu, Jingcheng, Dutta, Subhabrata, Elshabrawy, Ahmed, Madabushi, Harish Tayyar, Gurevych, Iryna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912632153309184
author Niu, Jingcheng
Dutta, Subhabrata
Elshabrawy, Ahmed
Madabushi, Harish Tayyar
Gurevych, Iryna
author_facet Niu, Jingcheng
Dutta, Subhabrata
Elshabrawy, Ahmed
Madabushi, Harish Tayyar
Gurevych, Iryna
contents Large-scale Transformer language models (LMs) trained solely on next-token prediction with web-scale data can solve a wide range of tasks after seeing just a few examples. The mechanism behind this capability, known as in-context learning (ICL), remains both controversial and poorly understood. Some studies argue that it is merely the result of memorizing vast amounts of data, while others contend that it reflects a fundamental, symbolic algorithmic development in LMs. In this work, we introduce a suite of investigative tasks and a novel method to systematically investigate ICL by leveraging the full Pythia scaling suite, including interim checkpoints that capture progressively larger amount of training data. By carefully exploring ICL performance on downstream tasks and simultaneously conducting a mechanistic analysis of the residual stream's subspace, we demonstrate that ICL extends beyond mere "memorization" of the training corpus, yet does not amount to the implementation of an independent symbolic algorithm. Our results also clarify several aspects of ICL, including the influence of training dynamics, model capabilities, and elements of mechanistic interpretability. Overall, our work advances the understanding of ICL and its implications, offering model developers insights into potential improvements and providing AI security practitioners with a basis for more informed guidelines.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
Niu, Jingcheng
Dutta, Subhabrata
Elshabrawy, Ahmed
Madabushi, Harish Tayyar
Gurevych, Iryna
Computation and Language
Artificial Intelligence
Large-scale Transformer language models (LMs) trained solely on next-token prediction with web-scale data can solve a wide range of tasks after seeing just a few examples. The mechanism behind this capability, known as in-context learning (ICL), remains both controversial and poorly understood. Some studies argue that it is merely the result of memorizing vast amounts of data, while others contend that it reflects a fundamental, symbolic algorithmic development in LMs. In this work, we introduce a suite of investigative tasks and a novel method to systematically investigate ICL by leveraging the full Pythia scaling suite, including interim checkpoints that capture progressively larger amount of training data. By carefully exploring ICL performance on downstream tasks and simultaneously conducting a mechanistic analysis of the residual stream's subspace, we demonstrate that ICL extends beyond mere "memorization" of the training corpus, yet does not amount to the implementation of an independent symbolic algorithm. Our results also clarify several aspects of ICL, including the influence of training dynamics, model capabilities, and elements of mechanistic interpretability. Overall, our work advances the understanding of ICL and its implications, offering model developers insights into potential improvements and providing AI security practitioners with a basis for more informed guidelines.
title Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.11004