RaFe: Ranking Feedback Improves Query Rewriting for RAG

TL;DR

This paper introduces RaFe, a framework that enhances query rewriting in RAG systems by utilizing ranking feedback from a reranker, eliminating the need for annotated data and improving performance.

Contribution

RaFe is a novel, annotation-free framework that leverages ranking feedback from rerankers to improve query rewriting in RAG systems.

Findings

RaFe outperforms baseline methods in query rewriting tasks.

Utilizing ranking feedback improves the quality of rewritten queries.

The framework reduces reliance on annotated data for training.

Abstract

As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a framework for training query rewriting models free of annotations. By leveraging a publicly available reranker, ours~provides feedback aligned well with the rewriting objectives. Experimental results demonstrate that ours~can obtain better performance than baselines.