Language Model for Large-Text Transmission in Noisy Quantum Communications

Yuqi Li, Zhouhang Shi, Haitao Ma, Li Shen, Jinge Bao, Yunlong Xiao

Keywords: Language Model; Noisy Superdense Coding; Text Transmission

TL;DR: Language-model-assisted quantum communication protocols can substantially improve the efficiency of large-scale text transmission.

Abstract: Quantum communication has the potential to revolutionise information processing, providing unparalleled security and increased capacity compared to its classical counterpart by using the principles of quantum mechanics. However, the presence of errors poses a significant challenge to realising these advantages. While strategies like quantum error correction and quantum error mitigation have been developed to address these errors, they often come with substantial overhead, hindering the practical transmission of large texts. Here, we introduce an application of machine learning frameworks for natural language processing to enhence the performance of noisy quantum communications, particularly superdense coding. Using BERT, a model known for its capabilities in natural language processing, we demonstrate that language-model-assisted quantum communication protocols can substantially improve the efficiency of large-scale information transmission. This brings us closer to the practical realisation of a quantum internet.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9859