MoDEM: Mixture of Domain Expert Models

TL;DR

This paper introduces MoDEM, a system that uses a BERT-based router to direct prompts to domain-specific models, significantly improving performance and efficiency over general-purpose large language models.

Contribution

It presents a novel mixture of domain expert models with prompt routing, demonstrating improved performance and cost-efficiency over traditional large models.

Findings

Outperforms general-purpose models of similar size on benchmarks.

Reduces computational costs while maintaining high accuracy.

Supports a shift towards specialized, modular AI systems.

Abstract

We propose a novel approach to enhancing the performance and efficiency of large language models (LLMs) by combining domain prompt routing with domain-specialized models. We introduce a system that utilizes a BERT-based router to direct incoming prompts to the most appropriate domain expert model. These expert models are specifically tuned for domains such as health, mathematics and science. Our research demonstrates that this approach can significantly outperform general-purpose models of comparable size, leading to a superior performance-to-cost ratio across various benchmarks. The implications of this study suggest a potential paradigm shift in LLM development and deployment. Rather than focusing solely on creating increasingly large, general-purpose models, the future of AI may lie in developing ecosystems of smaller, highly specialized models coupled with sophisticated routing systems. This approach could lead to more efficient resource utilization, reduced computational costs, and superior overall performance.