Data Distributional Properties Drive Emergent In-Context Learning in Transformers

TL;DR

This paper investigates how specific distributional properties of training data, like burstiness and skewness, enable emergent in-context learning in transformer models, highlighting the interplay between data characteristics and model architecture.

Contribution

It reveals that naturalistic data distributions, especially skewed and bursty ones, are crucial for in-context learning emergence in transformers, contrasting with traditional i.i.d. training assumptions.

Findings

In-context learning emerges with bursty and skewed data distributions.

Models can learn both in-context and weight-based learning when trained on skewed data.

Naturalistic data distributions are effective only in transformers, not recurrent models.

Abstract

Large transformer-based models are able to perform in-context few-shot learning, without being explicitly trained for it. This observation raises the question: what aspects of the training regime lead to this emergent behavior? Here, we show that this behavior is driven by the distributions of the training data itself. In-context learning emerges when the training data exhibits particular distributional properties such as burstiness (items appear in clusters rather than being uniformly distributed over time) and having large numbers of rarely occurring classes. In-context learning also emerges more strongly when item meanings or interpretations are dynamic rather than fixed. These properties are exemplified by natural language, but are also inherent to naturalistic data in a wide range of other domains. They also depart significantly from the uniform, i.i.d. training distributions typically used for standard supervised learning. In our initial experiments, we found that in-context learning traded off against more conventional weight-based learning, and models were unable to achieve both simultaneously. However, our later experiments uncovered that the two modes of learning could co-exist in a single model when it was trained on data following a skewed Zipfian distribution -- another common property of naturalistic data, including language. In further experiments, we found that naturalistic data distributions were only able to elicit in-context learning in transformers, and not in recurrent models. In sum, our findings indicate how the transformer architecture works together with particular properties of the training data to drive the intriguing emergent in-context learning behaviour of large language models, and how future work might encourage both in-context and in-weights learning in domains beyond language.