Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs

The rapid advancement of Large Language Models (LLMs) has significantly enhanced performance across various natural language processing (NLP) tasks, yet the high computational costs and latency associated with deploying such models continue to pose critical bottlenecks, limiting their broader applicability. To mitigate these challenges, we propose a dynamic hybrid inference framework, Firewall Routing, which efficiently selects between a strong and a weak LLMs based on the complexity of the query. A lightweight routing model is trained to optimize resource allocation by learning from response quality and preventing longtail queries, which are often too hard to solve by LLMs, from being routed to the stronger model. Moreover, our method incorporates multiple sampling to enhance query evaluation reliability while leveraging Hard Blocking and Soft Blocking to handle long-tail queries along with refining labels for model selection. Extensive experiments show our method outperforms existing routing strategies by up to 5.29% in APGR, demonstrating state-of-the-art performance across multiple benchmarks.