Quantum-Inspired Self-Attention in a Large Language Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kuznetsov, Nikita, Ismagilov, Niyaz, Campos, Ernesto
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914367482626048
author Kuznetsov, Nikita
Ismagilov, Niyaz
Campos, Ernesto
author_facet Kuznetsov, Nikita
Ismagilov, Niyaz
Campos, Ernesto
contents Recent advances in Natural Language Processing have been predominantly driven by transformer-based architectures, which rely heavily on self-attention mechanisms to model relationships between tokens in a sequence. Similarly, the field of Quantum Natural Language Processing, which seeks to leverage quantum principles to address challenges in language understanding and generation tasks, has seen the recent development of quantum self-attention mechanisms. We propose a classical quantum-inspired self-attention (QISA) mechanism and integrate it into the full autoregressive language modeling pipeline of GPT-1. To the best of our knowledge, this is the first integration of this kind, as previous quantum self-attention mechanisms have been primarily tested on text classification. In our experiments, QISA achieves better performance when compared to standard self-attention on the metrics character error rate ($15.5\times$ better), word error rate ($4.7 \times $) and cross-entropy loss ($13 \times$). This is achieved while only requiring a $ 2.6\times$ longer inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03318
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantum-Inspired Self-Attention in a Large Language Model
Kuznetsov, Nikita
Ismagilov, Niyaz
Campos, Ernesto
Computation and Language
Artificial Intelligence
Quantum Physics
Recent advances in Natural Language Processing have been predominantly driven by transformer-based architectures, which rely heavily on self-attention mechanisms to model relationships between tokens in a sequence. Similarly, the field of Quantum Natural Language Processing, which seeks to leverage quantum principles to address challenges in language understanding and generation tasks, has seen the recent development of quantum self-attention mechanisms. We propose a classical quantum-inspired self-attention (QISA) mechanism and integrate it into the full autoregressive language modeling pipeline of GPT-1. To the best of our knowledge, this is the first integration of this kind, as previous quantum self-attention mechanisms have been primarily tested on text classification. In our experiments, QISA achieves better performance when compared to standard self-attention on the metrics character error rate ($15.5\times$ better), word error rate ($4.7 \times $) and cross-entropy loss ($13 \times$). This is achieved while only requiring a $ 2.6\times$ longer inference time.
title Quantum-Inspired Self-Attention in a Large Language Model
topic Computation and Language
Artificial Intelligence
Quantum Physics
url https://arxiv.org/abs/2603.03318