AutoMix: Automatically Mixing Language Models
This work addresses the problem of efficiently leveraging multiple LLMs for users needing to balance cost and accuracy, though it is incremental as it builds on existing routing and verification techniques.
The paper tackles the challenge of optimizing computational cost and performance when using diverse large language models (LLMs) by introducing AutoMix, an approach that routes queries to larger models based on the approximate correctness of outputs from a smaller model. It reduces computational cost by over 50% while maintaining comparable performance across five models and datasets.
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and performance remains challenging. In this work, we present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM. Central to Automix are two key technical contributions. First, it has a few-shot self-verification mechanism, which estimates the reliability of its own outputs without requiring extensive training. Second, given that self-verification can be noisy, it employs a POMDP based router that can effectively select an appropriately sized model, based on answer confidence. Experiments across five language models and five challenging datasets show that Automix consistently surpasses strong baselines, reducing computational cost by over 50% for comparable performance.