Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models

TL;DR

This paper presents uRAG, a unified retrieval engine designed to support multiple retrieval-augmented generation systems, enabling large-scale experimentation and advancing understanding of machine search engines.

Contribution

The paper introduces uRAG, a generic framework with standardized training guidelines that supports diverse RAG systems and facilitates large-scale research on machine search engines.

Findings

uRAG enables effective support for multiple RAG tasks.

Large-scale ecosystem demonstrates the framework's versatility.

Research insights into promises and challenges of machine search engines.

Abstract

This paper introduces uRAG--a framework with a unified retrieval engine that serves multiple downstream retrieval-augmented generation (RAG) systems. Each RAG system consumes the retrieval results for a unique purpose, such as open-domain question answering, fact verification, entity linking, and relation extraction. We introduce a generic training guideline that standardizes the communication between the search engine and the downstream RAG systems that engage in optimizing the retrieval model. This lays the groundwork for us to build a large-scale experimentation ecosystem consisting of 18 RAG systems that engage in training and 18 unknown RAG systems that use the uRAG as the new users of the search engine. Using this experimentation ecosystem, we answer a number of fundamental research questions that improve our understanding of promises and challenges in developing search engines for machines.