SCA-LLM: Spectral-Attentive Channel Prediction with Large Language Models in MIMO-OFDM

2025-09-09

AI Summary

To address the domain mismatch problem inherent in large language models (LLMs) pretrained exclusively on textual data, this paper proposes a spectrum-domain-aware framework for channel prediction in MIMO-OFDM systems. The method introduces a spectral attention mechanism that explicitly incorporates frequency-domain channel state information (CSI) features into an LLM adapter, thereby bridging the semantic gap between non-textual wireless signals and language models. It employs a lightweight adapter-LLM architecture that jointly leverages spectral feature extraction, attention-based modeling, and sequence prediction capabilities. Experimental results demonstrate that the proposed approach achieves up to a 2.4 dB improvement in normalized mean square error (NMSE) over state-of-the-art methods, while exhibiting strong cross-scenario generalization performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In recent years, the success of large language models (LLMs) has inspired growing interest in exploring their potential applications in wireless communications, especially for channel prediction tasks. However, directly applying LLMs to channel prediction faces a domain mismatch issue stemming from their text-based pre-training. To mitigate this, the ``adapter + LLM" paradigm has emerged, where an adapter is designed to bridge the domain gap between the channel state information (CSI) data and LLMs. While showing initial success, existing adapters may not fully exploit the potential of this paradigm. To address this limitation, this work provides a key insight that learning representations from the spectral components of CSI features can more effectively help bridge the domain gap. Accordingly, we propose a spectral-attentive framework, named SCA-LLM, for channel prediction in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Specifically, its novel adapter can capture finer spectral details and better adapt the LLM for channel prediction than previous methods. Extensive simulations show that SCA-LLM achieves state-of-the-art prediction performance and strong generalization, yielding up to $-2.4~ ext{dB}$ normalized mean squared error (NMSE) advantage over the previous LLM based method. Ablation studies further confirm the superiority of SCA-LLM in mitigating domain mismatch.

Problem

• Bridging domain gap between LLMs and wireless channel data
• Improving channel prediction in MIMO-OFDM systems using spectral components
• Mitigating performance limitations of existing adapter methods for LLMs

Innovation

• Spectral-attentive adapter bridges domain gap
• Captures finer spectral details in CSI
• Enhances LLM for channel prediction performance