Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission
This addresses communication efficiency for edge-AI applications, though it is incremental as it builds on existing hybrid and federated learning methods.
The paper tackles the communication overhead in hybrid language models by proposing FedHLM, which integrates federated learning to optimize token-level uncertainty thresholds and uses peer-to-peer token reuse, reducing LLM transmissions by over 95% with minimal accuracy loss.
Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference, HLMs reduce latency and communication by invoking LLMs only when local SLM predictions are uncertain, i.e., when token-level confidence is low or entropy is high. However, ambiguous or low-confidence predictions still require frequent offloading to the LLM, leading to significant communication overhead in bandwidth-constrained settings. To address this, we propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL). FedHLM's key innovation lies in collaboratively learning token-level uncertainty thresholds that govern when LLM assistance is needed. Rather than using static or manually tuned thresholds, FedHLM employs FL to optimize these thresholds in a privacy-preserving, distributed manner. Additionally, it leverages embedding-based token representations for Peer-to-Peer (P2P) resolution, enabling clients to reuse tokens inferred by semantically similar peers without engaging the LLM. We further introduce hierarchical model aggregation: edge servers refine local routing policies through client updates, while cross-cluster coordination aligns global decision boundaries. This layered design captures recurring uncertainty patterns, reducing redundant LLM queries. Experiments on large-scale news classification tasks show that FedHLM reduces LLM transmissions by over 95 percent with negligible accuracy loss, making it well-suited for scalable and efficient edge-AI applications.