Related papers: Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models

URL: http://arxiv.org/abs/2411.07820v2
Date: Wed, 13 Nov 2024 05:43:58 GMT
Title: Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
Authors: Youan Cong, Cheng Wang, Pritom Saha Akash, Kevin Chen-Chuan Chang,
Abstract summary: The Extract-Refine-Retrieve-Read (ERRR) framework is designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems. Unlike conventional query optimization techniques used in RAG, the ERRR framework begins by extracting knowledge from Large Language Models (LLMs)
Score: 26.353428245346166
License:
Abstract: We introduce the Extract-Refine-Retrieve-Read (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the specific knowledge requirements of Large Language Models (LLMs). Unlike conventional query optimization techniques used in RAG, the ERRR framework begins by extracting parametric knowledge from LLMs, followed by using a specialized query optimizer for refining these queries. This process ensures the retrieval of only the most pertinent information essential for generating accurate responses. Moreover, to enhance flexibility and reduce computational costs, we propose a trainable scheme for our pipeline that utilizes a smaller, tunable model as the query optimizer, which is refined through knowledge distillation from a larger teacher model. Our evaluations on various question-answering (QA) datasets and with different retrieval systems show that ERRR consistently outperforms existing baselines, proving to be a versatile and cost-effective module for improving the utility and accuracy of RAG systems.