Fine-Tuning Lightweight LLM for Enhanced Network Understanding: A Rephrase and Contrast Approach
IEEE Transactions on Machine Learning in Communications and Networking · 2026 · 4 · 647-661
DOI: 10.1109/tmlcn.2026.3680410 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Machine Learning in Communications and Networking, 2026. Verfasst von Liujianfu Wang und 5 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2024 Shenzhen-Hong Kong-Macao Science and Technology Program (STIC), Category C Project, Jockey Club STEM Lab of Advanced Wireless Networks for Mission-Critical Automation and Intelligence funded by The Hong Kong Jockey Club Charities Trust..
Abstract (Originalsprache)
The application of Large Language Models (LLMs) to the domain of communication networks has emerged as a significant area of investigation for both academia and industry. However, progress in this field is constrained by two critical challenges: the limited generalization capabilities inherent in prompt-dependent techniques and a scarcity of efficient fine-tuning methodologies that can unlock the full potential of lightweight LLMs. To surmount these obstacles, this paper introduces Rephrase and Contrast (RaC), a novel fine-tuning framework designed to substantially enhance an LLM’s comprehension and logical reasoning abilities by systematically integrating question reformulation with a comparative evaluation of correct and incorrect responses. Our contributions are threefold. First, we present the RaC framework, whose efficacy is validated through extensive experimentation. The fine-tuned model demonstrates a 15.84% improvement in accuracy over its baseline counterpart when evaluated on a comprehensive benchmark of networking problems. Second, to facilitate robust model training, we developed a GPT-assisted data mining pipeline to generate high-fidelity question-answer (QA) pairs from established networking textbooks, creating a comprehensive dataset. We further introduce ChoiceBoost-X, a data augmentation technique designed to expand this dataset while mitigating positional bias in multiple-choice formats. Third, to foster reproducible research and community-driven innovation, we are releasing our complete toolchain as open-source, including: 1) a LLaMA3.1-8B model specifically fine-tuned for networking QA; 2) the curated training dataset from textbooks; and 3) multi-difficulty test sets to serve as a standardized benchmark for future studies.
Förderung
- 2024 Shenzhen-Hong Kong-Macao Science and Technology Program (STIC), Category C Project
- Jockey Club STEM Lab of Advanced Wireless Networks for Mission-Critical Automation and Intelligence funded by The Hong Kong Jockey Club Charities Trust.
Zitieren
APA
Wang, L., Lin, J., Du, Y., Pan, Y., Chen, K., & Liew, S. C. (2026). Fine-Tuning Lightweight LLM for Enhanced Network Understanding: A Rephrase and Contrast Approach. IEEE Transactions on Machine Learning in Communications and Networking, 4, 647-661. https://doi.org/10.1109/tmlcn.2026.3680410
Vancouver
Wang L, Lin J, Du Y, Pan Y, Chen K, Liew SC. Fine-Tuning Lightweight LLM for Enhanced Network Understanding: A Rephrase and Contrast Approach. IEEE Transactions on Machine Learning in Communications and Networking. 2026;4:647-661. doi:10.1109/tmlcn.2026.3680410
BibTeX
@article{Wang2026,
author = {Wang, Liujianfu and Lin, Jingqi and Du, Yuyang and Pan, Yuchen and Chen, Kexin and Liew, Soung Chang},
title = {Fine-Tuning Lightweight LLM for Enhanced Network Understanding: A Rephrase and Contrast Approach},
journal = {IEEE Transactions on Machine Learning in Communications and Networking},
year = {2026},
volume = {4},
pages = {647--661},
doi = {10.1109/tmlcn.2026.3680410}
}
EUVIMED