Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hou, Qiushuo, Park, Sangwoo, Zecchin, Matteo, Cai, Yunlong, Yu, Guanding, Simeone, Osvaldo, Melodia, Tommaso
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917473688748032
author Hou, Qiushuo
Park, Sangwoo
Zecchin, Matteo
Cai, Yunlong
Yu, Guanding
Simeone, Osvaldo
Melodia, Tommaso
author_facet Hou, Qiushuo
Park, Sangwoo
Zecchin, Matteo
Cai, Yunlong
Yu, Guanding
Simeone, Osvaldo
Melodia, Tommaso
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20012
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
Hou, Qiushuo
Park, Sangwoo
Zecchin, Matteo
Cai, Yunlong
Yu, Guanding
Simeone, Osvaldo
Melodia, Tommaso
Signal Processing
Machine Learning
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.
title Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2512.20012