LLM4SG: Adapting Large Language Model for Scatterer Generation via Synesthesia of Machines

TL;DR

This paper introduces LLM4SG, a novel large language model-based method for scatterer generation in 6G AI-native communications, utilizing synthetic datasets and cross-modal learning to outperform traditional models.

Contribution

The paper presents a new LLM-based approach with a specialized architecture and synthetic dataset for accurate scatterer generation in V2V communications, enhancing generalization and data quality.

Findings

LLM4SG outperforms ray-tracing and deep learning models in scatterer generation.

The model demonstrates strong cross-condition generalization across scenarios and frequency bands.

Synthetic dataset SynthSoM-V2V effectively supports training for 6G communication applications.

Abstract

In this paper, a novel large language model (LLM)-based method for scatterer generation (LLM4SG) is proposed for sixth-generation (6G) artificial intelligence (AI)-native communications. To provide a solid data foundation, we construct a new synthetic intelligent sensing-communication dataset for Synesthesia of Machines (SoM) in vehicle-to-vehicle (V2V) communications, named SynthSoM-V2V, covering multiple V2V scenarios with multiple frequency bands and multiple vehicular traffic densities (VTDs). Leveraging the powerful cross-modal representation capabilities of LLMs, LLM4SG is designed to capture the general mapping relationship from light detection and ranging (LiDAR) point clouds to electromagnetic scatterers via SoM. To address the inherent and significant differences across multi-modal data, synergistically optimized four-module architecture, i.e., preprocessor, embedding, backbone, and output modules, are designed by considering sensing characteristics and electromagnetic propagation. The embedding module achieves effective cross-domain alignment of the sensing-communication domain and the natural language domain.The backbone network is adapted in a task-guided manner with low rank adaptation (LoRA), where a carefully selected subset of layers is fine tuned to preserve general knowledge and reduce training cost. The proposed LLM4SG is evaluated for scatterer generation by benchmarking against ray-tracing (RT) and conventional deep learning models. Simulation results demonstrate that the proposed LLM4SG achieves superior performance in both full-sample and cross-condition generalization testing. It significantly outperforms conventional deep learning models across different frequency bands, scenarios, and VTDs, and demonstrates the capability to provide the massive and high-quality channel small-scale fading data required by AI-native 6G systems.