RaFe: Ranking Feedback Improves Query Rewriting for RAG

• DOI: 10.48550/arxiv.2405.14431
• Publication Date: 2024-05-23
• Authors: Shengyu Mao; Yong Jiang; Boli Chen; Xiao Li; Peng Wang; Xinyu Wang; Pengjun Xie; Fei Huang; Huajun Chen; Ningyu Zhang
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL); Information Retrieval (cs.IR); Computer Science - Information Retrieval

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 attempted to utilize small models with reinforcement learning rather than costly LLMs improve rewriting. However, current methods require annotations (e.g., labeled relevant documents or answers) predesigned rewards feedback, which lack generalization, fail signals tailored In this paper, we propose ours, a framework training free of annotations. By leveraging publicly available reranker, ours~provides feedback aligned well objectives. Experimental results demonstrate that ours~can obtain better performance baselines.