Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
This addresses the problem of inefficient query retrieval in RAG systems for users relying on LLMs, though it appears incremental as it builds on existing query optimization techniques.
The paper tackles the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems by introducing the ERRR framework, which optimizes queries through parametric knowledge extraction and refinement, resulting in improved accuracy and utility across QA datasets and retrieval systems.
We introduce the \textit{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.