ORI: O Routing Intelligence
This work addresses the problem of handling diverse tasks for developers and users of large language models, offering a scalable solution.
The authors tackled the challenge of a single large language model being insufficient for a wide range of tasks and achieved accuracy gains of up to 2.7 points on MMLU and 1.8 points on MuSR. ORI outperformed the strongest individual models and tied the top performance on ARC and BBH.
Single large language models (LLMs) often fall short when faced with the ever-growing range of tasks, making a single-model approach insufficient. We address this challenge by proposing ORI (O Routing Intelligence), a dynamic framework that leverages a set of LLMs. By intelligently routing incoming queries to the most suitable model, ORI not only improves task-specific accuracy, but also maintains efficiency. Comprehensive evaluations across diverse benchmarks demonstrate consistent accuracy gains while controlling computational overhead. By intelligently routing queries, ORI outperforms the strongest individual models by up to 2.7 points on MMLU and 1.8 points on MuSR, ties the top performance on ARC, and on BBH. These results underscore the benefits of a multi-model strategy and demonstrate how ORI's adaptive architecture can more effectively handle diverse tasks, offering a scalable, high-performance solution for a system of multiple large language models.