CL-SEC: Cross-Layer Semantic Error Correction Empowered by Language Models

2026-03-27

AI Summary

This work proposes CL-SEC, a cross-layer semantic error correction framework that addresses the limitations of existing methods, which rely solely on application-layer context and neglect physical-layer information, thereby struggling to accurately reconstruct the original transmitted text. CL-SEC is the first to integrate physical- and application-layer signals through joint modeling with a language model and employs a Bayesian product strategy tailored for cross-layer fusion to enable character-level recovery. By transcending the constraints of single-layer processing, the proposed approach achieves significant improvements over state-of-the-art methods in terms of bit error rate, word error rate, and semantic fidelity, enabling high-precision reconstruction of the original message.

Abstract

Achieving reliable communication has long been a fundamental challenge in networked systems. Semantic Error Correction (SEC) leverages the semantic understanding capabilities of language models (LMs) to perform application-layer error correction, complementing conventional channel decoding. While promising, existing SEC approaches rely solely on context captured by LMs at the application layer, ignoring the rich information available at the physical layer. To address this limitation, this paper introduces Cross-Layer SEC (CL-SEC), an LM-empowered error correction framework that integrates cross-layer information from both the physical and application layers to jointly correct corrupted words in text communication. Using a Bayesian combination in product form tailored to this framework, CL-SEC achieves significantly improved performance over methods that process information in isolated layers. CL-SEC shows substantial gains across multiple error-correction metrics, including bit-error rate, word-error rate, and semantic fidelity scores. Importantly, unlike most semantic communication systems that focus solely on recovering the semantic meaning of transmitted messages, CL-SEC aims to reconstruct the original transmitted message verbatim, leveraging the semantic understanding capabilities of LMs for precise reconstruction.

Problem

• Semantic Error Correction
• Cross-Layer Information
• Language Models
• Reliable Communication
• Message Reconstruction

Innovation

• Cross-Layer Semantic Error Correction
• Language Models
• Bayesian Fusion
• Physical-Application Layer Integration
• Verbatim Message Reconstruction