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

arXiv:2405.00175v1 Announce Type: new
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 …

abstract arxiv cs.cl cs.ir domain extraction framework language language models large language large language models machines multiple paper question question answering rag ranking results retrieval retrieval-augmented search search engine systems type unique verification