Paper reveals NNs implicitly build symbolic structures in vector space

RTomMcCoy · x · 2026-09-02

The paper 'The Emergent Symbolic Structure of Artificial Neural Networks' proposes that neural networks implicitly realize symbolic structure within their vector representations. It shows that a network's vector generation process can be approximated by a closed-form symbolic equation without changing behavior significantly. This holds for both small models and LLMs in math, logic, code, and language.

Related event: Eight-Year Study Finds Implicit Symbolic Structure Inside LLM Representations(4 posts)→

Original post →

More from Models

Models channel →