Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models

TL;DR

This paper proposes an 'Expert Orchestration' framework that democratizes and improves language model capabilities by intelligently selecting specialized models for specific tasks, enhancing performance, safety, and transparency.

Contribution

It introduces a novel framework that replaces monolithic models with an orchestrated system of specialized models, improving flexibility, safety, and democratization in language model deployment.

Findings

EO outperforms large generalist models in targeted tasks

Enhanced transparency and control in model selection

Supports democratic participation in AI development

Abstract

This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" (EO) framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from many existing models based on query requirements and decomposition, focusing on identifying what models do well rather than how they work internally. Independent "judge" models assess various models' capabilities across dimensions that matter to users, while "router" systems direct queries to the most appropriate specialists within an approved set. This approach delivers superior performance by leveraging targeted expertise rather than forcing costly generalist models to address all user requirements. EO enhances transparency, control, alignment, performance, safety and democratic participation through intelligent model selection.