LLM4MG: adapting large language model for multipath generation via synesthesia of machines

Abstract

Based on Synesthesia of Machines (SoM), a large language model (LLM) is adapted for multipath generation (LLM4MG) for the first time. Considering a sixth-generation (6G) vehicle-to-infrastructure (V2I) scenario, a new multi-modal sensing-communication dataset is constructed, named SynthSoM-V2I. Based on the SynthSoM-V2I dataset, the proposed LLM4MG leverages Large Language Model Meta AI (LLaMA) 3.2 for multipath generation via multi-modal sensory data. The proposed LLM4MG aligns the multi-modal feature space with the LLaMA semantic space through feature extraction and fusion networks. To achieve general knowledge transfer from the pre-trained LLaMA for multipath generation via multi-modal sensory data, the low-rank adaptation (LoRA) parameter-efficient fine-tuning and propagation-aware prompt engineering are exploited. Simulation results demonstrate that the proposed LLM4MG outperforms conventional deep learning-based methods in terms of line-of-sight (LoS)/non-LoS (NLoS) classification, multipath power/delay generation precision, and cross-vehicular traffic density (VTD), cross-band, and cross-scenario generalization. The utility of proposed LLM4MG is validated by real-world generalization.