How Do Transformers Learn Variable Binding in Symbolic Programs?

Yiwei Wu; Atticus Geiger; Raphaël Millière

2025 ICML ICML 2025

How Do Transformers Learn Variable Binding in Symbolic Programs?

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

Authors

Yiwei Wu, Atticus Geiger, Raphaël Millière

Topics

Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Transformers Artificial Intelligence > Core AI > Reasoning

Keywords

transformer attention head residual stream variable binding assignment chains dereferencing

Download PDF