Towards Atoms of Large Language Models 事件

Towards Atoms of Large Language Models arXiv:2509.20784v3 Announce Type: replace Abstract: The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underlying mechanisms. In this paper, we introduce Atom Theory to systematically define, evaluate, and identify such FRUs, which we term atoms. Building on the atomic inner product (AIP), a non-Euclidean metric that captures the underlying geometry of LLM representations,