MétaCan
Menu
Back to cohort
Record W4415293221 · doi:10.1109/mwc.2025.3596934

SpectrumLLM: Large Language Models for Next-Generation Spectrum Prediction

2025· article· W4415293221 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueIEEE Wireless Communications · 2025
Typearticle
Language
FieldComputer Science
TopicComputational Physics and Python Applications
Canadian institutionsWestern University
Fundersnot available
KeywordsWirelessGeneralizationAdaptabilityField (mathematics)Interference (communication)Spectrum managementWireless networkSpectrum (functional analysis)

Abstract

fetched live from OpenAlex

With the emergence of dynamic spectrum sharing in 5G networks, spectrum prediction (SP) has become essential for proactive spectrum management, reducing interference and optimizing dynamic spectrum access (DSA). However, existing SP methods often struggle to achieve high accuracy and generalization due to the complexity and rapidly evolving nature of modern wireless environments. Large Language Models (LLMs), as a significant breakthrough in the field of artificial intelligence, have demonstrated exceptional capabilities in handling time-series data and multi-modal tasks. This article presents the first exploration of integrating LLMs with SP, introducing a SpectrumLLM architecture that aligns radio spectrum state (RSS) series with the text space of LLMs for more efficient SP by applying tokenization, embedding and prompt engineering. Experimental evaluations demonstrate that LLMs significantly outperform traditional SP methods such as DLinear, Autoformer, and LSTM, offering superior adaptability and predictive accuracy. The findings highlight the potential of LLMs in revolutionizing SP for next-generation wireless systems, paving the way for intelligent spectrum management in future 5G-advanced and 6G networks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.965
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0030.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.056
GPT teacher head0.309
Teacher spread0.253 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it