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.
@article{arxiv.2604.08419,
title = {Real-Time Cross-Layer Semantic Error Correction Using Language Models and Software-Defined Radio},
author = {Yuchen Pan and Yuyang Du and Yirun Wang and Shiqi Xu and Lihao Zhang and Soung Chang Liew},
journal= {arXiv preprint arXiv:2604.08419},
year = {2026}
}