Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
IEEE Transactions on Communications · 2026 · 74 · 9713-9728
DOI: 10.1109/tcomm.2026.3700473 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2026. Verfasst von Qiushuo Hou und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, EPSRC Open Fellowship, EPSRC project.
Abstract (Originalsprache)
Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretation, and network optimization. However, their deployment in practice must balance inference cost, latency, and reliability. In this work, we study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline. In it, an efficient edge model handles routine queries, a more capable cloud model addresses complex cases, and human experts are involved only when necessary. We define a misalignment-cost constrained optimization problem, aiming to minimize average processing cost, while guaranteeing alignment of automated answers with expert judgments. We propose a statistically rigorous threshold selection method based on multiple hypothesis testing (MHT) for a query processing mechanism based on knowledge and confidence tests. The approach provides finite-sample guarantees on misalignment risk. Experiments on the TeleQnA dataset–a telecom-specific benchmark–demonstrate that the proposed method achieves superior cost-efficiency compared to conventional cascaded baselines, while ensuring reliability at prescribed confidence levels.
Förderung
- National Natural Science Foundation of China
- EPSRC Open Fellowship
- EPSRC project
- National Science Foundation
Zitieren
APA
Hou, Q., Park, S., Zecchin, M., Cai, Y., Yu, G., Simeone, O., & Melodia, T. (2026). Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems. IEEE Transactions on Communications, 74, 9713-9728. https://doi.org/10.1109/tcomm.2026.3700473
Vancouver
Hou Q, Park S, Zecchin M, Cai Y, Yu G, Simeone O, et al. Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems. IEEE Transactions on Communications. 2026;74:9713-9728. doi:10.1109/tcomm.2026.3700473
BibTeX
@article{Hou2026,
author = {Hou, Qiushuo and Park, Sangwoo and Zecchin, Matteo and Cai, Yunlong and Yu, Guanding and Simeone, Osvaldo and Melodia, Tommaso},
title = {Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems},
journal = {IEEE Transactions on Communications},
year = {2026},
volume = {74},
pages = {9713--9728},
doi = {10.1109/tcomm.2026.3700473}
}
EUVIMED