Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
This addresses the problem of scaling RAG systems for more accurate question-answering, representing an incremental improvement with specific gains.
The paper tackles the challenge of improving RAG accuracy as document corpora scale by proposing 'Blended RAG', which combines semantic search techniques and hybrid query strategies. It achieves better retrieval results on IR datasets like NQ and TREC-COVID and demonstrates superior performance on Generative Q&A datasets like SQUAD, even surpassing fine-tuning.
Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q\&A (Question-Answering) systems. However, RAG accuracy becomes increasingly challenging as the corpus of documents scales up, with Retrievers playing an outsized role in the overall RAG accuracy by extracting the most relevant document from the corpus to provide context to the LLM. In this paper, we propose the 'Blended RAG' method of leveraging semantic search techniques, such as Dense Vector indexes and Sparse Encoder indexes, blended with hybrid query strategies. Our study achieves better retrieval results and sets new benchmarks for IR (Information Retrieval) datasets like NQ and TREC-COVID datasets. We further extend such a 'Blended Retriever' to the RAG system to demonstrate far superior results on Generative Q\&A datasets like SQUAD, even surpassing fine-tuning performance.