Physical models realizing the transformer architecture of large language models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Chen, Zeqian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913951959220224
author Chen, Zeqian
author_facet Chen, Zeqian
contents The introduction of the transformer architecture in 2017 marked the most striking advancement in natural language processing. The transformer is a model architecture relying entirely on an attention mechanism to draw global dependencies between input and output. However, we believe there is a gap in our theoretical understanding of what the transformer is, and how it works physically. From a physical perspective on modern chips, such as those chips under 28nm, modern intelligent machines should be regarded as open quantum systems beyond conventional statistical systems. Thereby, in this paper, we construct physical models realizing large language models based on a transformer architecture as open quantum systems in the Fock space over the Hilbert space of tokens. Our physical models underlie the transformer architecture for large language models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physical models realizing the transformer architecture of large language models
Chen, Zeqian
Machine Learning
Artificial Intelligence
Computation and Language
Mathematical Physics
The introduction of the transformer architecture in 2017 marked the most striking advancement in natural language processing. The transformer is a model architecture relying entirely on an attention mechanism to draw global dependencies between input and output. However, we believe there is a gap in our theoretical understanding of what the transformer is, and how it works physically. From a physical perspective on modern chips, such as those chips under 28nm, modern intelligent machines should be regarded as open quantum systems beyond conventional statistical systems. Thereby, in this paper, we construct physical models realizing large language models based on a transformer architecture as open quantum systems in the Fock space over the Hilbert space of tokens. Our physical models underlie the transformer architecture for large language models.
title Physical models realizing the transformer architecture of large language models
topic Machine Learning
Artificial Intelligence
Computation and Language
Mathematical Physics
url https://arxiv.org/abs/2507.13354