Toward Understanding In-context vs. In-weight Learning
Keywords: In-context learning, generalization error, transformers
TL;DR: We propose a theoretical explanation on when a model will choose in-context learning vs in-weight learning and support the explanation with experiments.
Abstract: It has recently been demonstrated empirically that in-context learning
emerges in transformers when certain distributional properties are present in the training data, but this ability can also diminish upon further training.
We provide a new theoretical understanding of these phenomena by identifying simplified distributional properties that give rise to the emergence and eventual disappearance of in-context learning.
We do so by first analyzing a simplified model that uses a gating mechanism to choose between an in-weight and an in-context predictor.
Through a combination of a generalization error and regret analysis we identify conditions where in-context and in-weight learning emerge.
These theoretical findings are then corroborated experimentally by comparing the behaviour of a full transformer on the simplified distributions to that of the stylized model, demonstrating aligned results.
We then extend the study to a full large language model,
showing how fine-tuning on various collections of natural language prompts can elicit similar in-context and in-weight learning behaviour.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13085
Loading