Semantic Fidelity for Intelligent 6G Communication: A Taxonomic Deep Dive into Knowledge-Driven Architectures, Benchmarks, and Challenges

Abstract

Cognitive-semantic communication encodes task-relevant meaning rather than raw bits, improving 6G spectral efficiency and reducing latency, yet evidence remains fragmented across methods, evaluations, and deployments. This PRISMA-based review screens 782 records (2019-2025) from seven databases, retaining 73 studies organized into five method families: neural semantic codecs, KG-based pipelines, LLM-assisted codecs, cross-modal encoders, and semantic relays. We examine how goal-oriented semantics, knowledge graphs, and LLMs shape representation, compression, and task quality under rate and latency constraints across UAVs, NTNs, ISAC, Metaverse, and IoT. Reported gains include bandwidth reductions of 20-60% over conventional baselines, task accuracy improvements of 8-23 percentage points over bit-level systems, and cross-modal alignment scores above 0.80; however, these gains derive predominantly from AWGN simulations, and robustness under realistic fading, mobility, and adversarial conditions remains the most critical open problem. Gaps include narrow datasets, inconsistent metric definitions, and unaddressed security, privacy, and standardization concerns. Recommendations include shared multimodal datasets with channel traces, standardized robustness protocols, unified metric cards pairing task outcomes with resource costs, edge-friendly split designs, and integrity checks with privacy audits.