Real-Time Cross-Layer Semantic Error Correction Using Language Models and Software-Defined Radio

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Yuchen, Du, Yuyang, Wang, Yirun, Xu, Shiqi, Zhang, Lihao, Liew, Soung Chang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914461783162880
author Pan, Yuchen
Du, Yuyang
Wang, Yirun
Xu, Shiqi
Zhang, Lihao
Liew, Soung Chang
author_facet Pan, Yuchen
Du, Yuyang
Wang, Yirun
Xu, Shiqi
Zhang, Lihao
Liew, Soung Chang
contents As Language Models (LMs) advance, Semantic Error Correction (SEC) has emerged as a promising approach for reliable network designs. Yet existing methods prioritize intent over accuracy, falling short of verbatim recovery. Our recent work, Cross-Layer SEC (CL-SEC), addressed this by fusing physical-layer Log-Likelihood Ratios (LLRs) with semantic context, but its real-time feasibility remained unvalidated. This paper demonstrates CL-SEC on a live Software-Defined Radio (SDR) testbed, resolving implementation barriers with: 1) an SDR middleware enabling real-time LLR extraction from FPGA hardware, and 2) a generalized inference interface supporting modern encoder-decoder LMs. Real-world experiments confirm that the cross-layer fusion significantly outperforms either source alone.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08419
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Real-Time Cross-Layer Semantic Error Correction Using Language Models and Software-Defined Radio
Pan, Yuchen
Du, Yuyang
Wang, Yirun
Xu, Shiqi
Zhang, Lihao
Liew, Soung Chang
Networking and Internet Architecture
As Language Models (LMs) advance, Semantic Error Correction (SEC) has emerged as a promising approach for reliable network designs. Yet existing methods prioritize intent over accuracy, falling short of verbatim recovery. Our recent work, Cross-Layer SEC (CL-SEC), addressed this by fusing physical-layer Log-Likelihood Ratios (LLRs) with semantic context, but its real-time feasibility remained unvalidated. This paper demonstrates CL-SEC on a live Software-Defined Radio (SDR) testbed, resolving implementation barriers with: 1) an SDR middleware enabling real-time LLR extraction from FPGA hardware, and 2) a generalized inference interface supporting modern encoder-decoder LMs. Real-world experiments confirm that the cross-layer fusion significantly outperforms either source alone.
title Real-Time Cross-Layer Semantic Error Correction Using Language Models and Software-Defined Radio
topic Networking and Internet Architecture
url https://arxiv.org/abs/2604.08419