RFG Framework: Retrieval-Feedback-Grounded Multi-Query Expansion

Ronaldinho Vega Centeno Olivera, Allan M. de Souza, Allan M. de Souza, Julio Cesar dos Reis, Julio Cesar dos Reis

2025

Abstract

Information Retrieval (IR) systems face challenges such as query ambiguity and lexical mismatch, which limit the effectiveness of dense retrieval models, whose generalization capability to new domains or tasks is often limited. This study proposes a novel query expansion framework, named RFG, which integrates the capabilities of Large Language Models (LLMs) into an architecture that combines Retrieval-Augmented Generation (RAG) with Pseudo-Relevance Feedback (PRF). Our solution is based on using an initial document retrieval as a grounding context for the LLMs, a process that mitigates the generation of unsubstantiated information (“hallucinations”) by guiding the creation of a diverse set of pseudo-queries. Following an evaluation across a broad spectrum of retrieval models, including unsupervised and supervised dense models, our experimental results demonstrate that RFG consistently outperforms baseline methods, such as HyDE and Query2doc. In contrast to previous findings that suggest a negative correlation between retriever performance and query expansion benefits, this study originally reveals that our approach not only benefits models with lower initial effectiveness but also improves the results of more robust retrievers. This positions the generation of multiple, contextualized queries as a versatile and highly effective expansion strategy.

Paper Citation

in Harvard Style

Vega Centeno Olivera R., de Souza A. and dos Reis J. (2025). RFG Framework: Retrieval-Feedback-Grounded Multi-Query Expansion. In Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN , SciTePress, pages 509-516. DOI: 10.5220/0013836900004000

in Bibtex Style

@conference{kdir25,
author={Ronaldinho Vega Centeno Olivera and Allan de Souza and Julio dos Reis},
title={RFG Framework: Retrieval-Feedback-Grounded Multi-Query Expansion},
booktitle={Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2025},
pages={509-516},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013836900004000},
isbn={},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - RFG Framework: Retrieval-Feedback-Grounded Multi-Query Expansion
SN -
AU - Vega Centeno Olivera R.
AU - de Souza A.
AU - dos Reis J.
PY - 2025
SP - 509
EP - 516
DO - 10.5220/0013836900004000
PB - SciTePress