Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-Enabled Data Transmission in End-to-End Semantic Communication

Shavbo Salehi, Melike Erol-Kantarci, Dusit Niyato

TL;DR

This work addresses the data-efficiency challenge in end-to-end semantic communication for text by introducing KG-LLM, a framework that combines knowledge-graph based preprocessing with large-language-model encoding and BERT-based refinement. The approach compresses semantic content while preserving meaning, achieving about $30\%$ data reduction and up to $84\%$ semantic similarity, outperforming DL-based baselines like DeepSC and GPT-2. Through SST2-based experiments and comparisons across multiple LLM variants, KG-LLM demonstrates improved semantic fidelity and robustness across SNRs, with explicit trade-offs between compression and clarity. The method promises practical gains for 6G-era wireless systems where transmitting meaningful content efficiently and reliably is critical, particularly for real-time language-intensive applications.

Abstract

Emerging services such as augmented reality (AR) and virtual reality (VR) have increased the volume of data transmitted in wireless communication systems, revealing the limitations of traditional Shannon theory. To address these limitations, semantic communication has been proposed as a solution that prioritizes the meaning of messages over the exact transmission of bits. This paper explores semantic communication for text data transmission in end-to-end (E2E) systems through a novel approach called KG-LLM semantic communication, which integrates knowledge graph (KG) extraction and large language model (LLM) coding. In this method, the transmitter first utilizes a KG to extract key entities and relationships from sentences. The extracted information is then encoded using an LLM to obtain the semantic meaning. On the receiver side, messages are decoded using another LLM, while a bidirectional encoder representations from transformers (i.e., BERT) model further refines the reconstructed sentences for improved semantic similarity. The KG-LLM semantic communication method reduces the transmitted text data volume by 30% through KG-based compression and achieves 84\% semantic similarity between the original and received messages. This demonstrates the KG-LLM methods efficiency and robustness in semantic communication systems, outperforming the deep learning-based semantic communication model (DeepSC), which achieves only 63%.

LLM-Enabled Data Transmission in End-to-End Semantic Communication

TL;DR

This work addresses the data-efficiency challenge in end-to-end semantic communication for text by introducing KG-LLM, a framework that combines knowledge-graph based preprocessing with large-language-model encoding and BERT-based refinement. The approach compresses semantic content while preserving meaning, achieving about data reduction and up to semantic similarity, outperforming DL-based baselines like DeepSC and GPT-2. Through SST2-based experiments and comparisons across multiple LLM variants, KG-LLM demonstrates improved semantic fidelity and robustness across SNRs, with explicit trade-offs between compression and clarity. The method promises practical gains for 6G-era wireless systems where transmitting meaningful content efficiently and reliably is critical, particularly for real-time language-intensive applications.

Abstract

Emerging services such as augmented reality (AR) and virtual reality (VR) have increased the volume of data transmitted in wireless communication systems, revealing the limitations of traditional Shannon theory. To address these limitations, semantic communication has been proposed as a solution that prioritizes the meaning of messages over the exact transmission of bits. This paper explores semantic communication for text data transmission in end-to-end (E2E) systems through a novel approach called KG-LLM semantic communication, which integrates knowledge graph (KG) extraction and large language model (LLM) coding. In this method, the transmitter first utilizes a KG to extract key entities and relationships from sentences. The extracted information is then encoded using an LLM to obtain the semantic meaning. On the receiver side, messages are decoded using another LLM, while a bidirectional encoder representations from transformers (i.e., BERT) model further refines the reconstructed sentences for improved semantic similarity. The KG-LLM semantic communication method reduces the transmitted text data volume by 30% through KG-based compression and achieves 84\% semantic similarity between the original and received messages. This demonstrates the KG-LLM methods efficiency and robustness in semantic communication systems, outperforming the deep learning-based semantic communication model (DeepSC), which achieves only 63%.

Paper Structure

This paper contains 13 sections, 6 equations, 2 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Literature Review
  3. System Model
  4. Proposed Method
  5. Pre-processing with Knowledge Graph
  6. Semantic Encoding with LLM
  7. Contextual Inference with LLM and BERT Embeddings
  8. Simulation Results
  9. Semantic Compression Rate
  10. Semantic Similarity
  11. Transmission Time
  12. BER and Semantic Similarity Across SNR Levels
  13. Conclusion

Figures (2)

  • Figure 1: System model of LLM-enabled semantic communication
  • Figure 2: Comparison of LLM-Based Semantic Communication Performance