Papers
arxiv:2611.13270

What drives the emergence of symbolic mechanisms in large language models?

Published on Nov 9
Authors:
,

Abstract

Data diversity, rather than architectural inductive biases, primarily drives the emergence of symbolic mechanisms in neural networks trained on abstract sequence tasks.

Recent work has identified a set of emergent symbolic mechanisms that support abstract reasoning in large language models, but it remains unclear what factors drive the emergence of these mechanisms. To address this question, we trained neural networks from scratch on abstract sequence tasks, varying both architectural and data distributional factors, and investigated the effects of these factors on the emergence of symbolic mechanisms. Using representational, attentional, and causal mediation analyses, we first confirmed that transformer-based language models trained from scratch on our task developed symbolic mechanisms. We then found that, across multiple axes of data diversity, greater diversity produced stronger symbolic signatures. Surprisingly, the same signatures emerged in modified transformer architectures and even multilayer perceptrons, indicating that architectural inductive biases are not necessary for the development of symbolic mechanisms. We also observed consistent patterns in an entity-attribute binding task. Together, these findings identify data diversity, not architecture, as the primary driver of emergent symbolic computation in neural networks.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.13270 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.13270 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.