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

TL;DR

CL-SEC is a novel framework that integrates physical and application layer information using language models to improve semantic error correction in text communication.

Contribution

It introduces a cross-layer approach combining physical and application layer data with language models, enhancing error correction beyond existing single-layer methods.

Findings

Significantly improved bit-error and word-error rates.

Achieved higher semantic fidelity scores.

Demonstrated effective joint correction across layers.

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.