Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
This work addresses cost-efficiency for users deploying LLMs in scenarios with varying quality requirements, though it is incremental as it builds on existing routing and model selection ideas.
The paper tackles the problem of high deployment costs for large language models (LLMs) by proposing a hybrid inference approach that routes queries between small and large models based on predicted difficulty and desired quality, achieving up to 40% fewer calls to the large model without quality loss.
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e.g., edge) devices, tend to lag behind in terms of response quality. Therefore in this work we propose a hybrid inference approach which combines their respective strengths to save cost and maintain quality. Our approach uses a router that assigns queries to the small or large model based on the predicted query difficulty and the desired quality level. The desired quality level can be tuned dynamically at test time to seamlessly trade quality for cost as per the scenario requirements. In experiments our approach allows us to make up to 40% fewer calls to the large model, with no drop in response quality.