Research

Paper

AI LLM March 03, 2026

Large Language Model Empowered CSI Feedback in Massive MIMO Systems

Authors

Jie Wu, Wei Xu, Le Liang, Xiaohu You, Mérouane Debbah

Abstract

Despite the success of large language models (LLMs) across domains, their potential for efficient channel state information (CSI) compression and feedback in frequency division duplex (FDD) massive multiple-input multiple-output (mMIMO) systems remains largely unexplored yet increasingly important. In this paper, we propose a novel LLM-based framework for CSI feedback to exploit the potential of LLMs. We first reformulate the CSI compression feedback task as a masked token prediction task that aligns more closely with the functionality of LLMs. Subsequently, we design an information-theoretic mask selection strategy based on self-information, identifying and selecting CSI elements with the highest self-information at the user equipment (UE) for feedback. This ensures that masked tokens correspond to elements with lower self-information, while visible tokens correspond to elements with higher self-information, thus maximizing the accuracy of LLM predictions.

Metadata

arXiv ID: 2603.02686
Provider: ARXIV
Primary Category: cs.IT
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.02686v1</id>\n    <title>Large Language Model Empowered CSI Feedback in Massive MIMO Systems</title>\n    <updated>2026-03-03T07:29:40Z</updated>\n    <link href='https://arxiv.org/abs/2603.02686v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.02686v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Despite the success of large language models (LLMs) across domains, their potential for efficient channel state information (CSI) compression and feedback in frequency division duplex (FDD) massive multiple-input multiple-output (mMIMO) systems remains largely unexplored yet increasingly important. In this paper, we propose a novel LLM-based framework for CSI feedback to exploit the potential of LLMs. We first reformulate the CSI compression feedback task as a masked token prediction task that aligns more closely with the functionality of LLMs. Subsequently, we design an information-theoretic mask selection strategy based on self-information, identifying and selecting CSI elements with the highest self-information at the user equipment (UE) for feedback. This ensures that masked tokens correspond to elements with lower self-information, while visible tokens correspond to elements with higher self-information, thus maximizing the accuracy of LLM predictions.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IT'/>\n    <published>2026-03-03T07:29:40Z</published>\n    <arxiv:primary_category term='cs.IT'/>\n    <author>\n      <name>Jie Wu</name>\n    </author>\n    <author>\n      <name>Wei Xu</name>\n    </author>\n    <author>\n      <name>Le Liang</name>\n    </author>\n    <author>\n      <name>Xiaohu You</name>\n    </author>\n    <author>\n      <name>Mérouane Debbah</name>\n    </author>\n  </entry>"
}