Adaptive Sparsification and FedAvg for Low-Latency LLM Inference in Federated Edge Networks

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: Can adaptive sparsification techniques combined with FedAvg improve inference latency and throughput for large language models in over-the-air federated learning scenarios without degrading alignment. In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications. 10 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Can adaptive sparsification techniques combined with FedAvg improve inference latency and throughput for large language models in over-the-air federated learning scenarios without degrading alignment scores?

Autonomous literature synthesis. Automated review score: 7.8/10. Full text and citation available at Assignee Research.