Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
This addresses the practical deployment challenges of LLMs in telecommunications for tasks like troubleshooting, but it is incremental as it builds on existing cascade methods with a novel threshold selection approach.
The paper tackled the problem of balancing cost, latency, and reliability in deploying LLMs for telecom automation by proposing an edge-cloud-expert cascade system, achieving superior cost-efficiency on the TeleQnA dataset while guaranteeing misalignment risk at prescribed confidence levels.
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.