@inproceedings{melo-etal-2025-dont,
title = "Don{'}t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering",
author = "Melo, Andre and
Chen, Enting and
Vougiouklis, Pavlos and
Diao, Chenxin and
Piramanayagam, Shriram and
Lai, Ruofei and
Pan, Jeff Z.",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.174/",
pages = "2564--2572",
ISBN = "979-8-89176-333-3",
abstract = "Traditional Retrieval-augmented Generation systems struggle with complex multi-hop questions, which often require reasoning over multiple passages. While GraphRAG approaches address these challenges, most of them rely on expensive LLM calls. In this paper, we propose $\text{GR\small{IEVER}}$, a lightweight, low-resource, multi-step graph-based retriever for multi-hop QA. Unlike prior work, $\text{GR\small{IEVER}}$ does not rely on LLMs and can perform multi-step retrieval in a few hundred milliseconds. It efficiently indexes passages alongside an associated knowledge graph and employs a hybrid retriever combined with aggressive filtering to reduce retrieval latency. Experiments on multi-hop QA datasets demonstrate that $\text{GR\small{IEVER}}$ outperforms conventional retrievers and shows strong potential as a base retriever within multi-step agentic frameworks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="melo-etal-2025-dont">
<titleInfo>
<title>Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enting</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavlos</namePart>
<namePart type="family">Vougiouklis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxin</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shriram</namePart>
<namePart type="family">Piramanayagam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruofei</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Traditional Retrieval-augmented Generation systems struggle with complex multi-hop questions, which often require reasoning over multiple passages. While GraphRAG approaches address these challenges, most of them rely on expensive LLM calls. In this paper, we propose \textGRIEVER, a lightweight, low-resource, multi-step graph-based retriever for multi-hop QA. Unlike prior work, \textGRIEVER does not rely on LLMs and can perform multi-step retrieval in a few hundred milliseconds. It efficiently indexes passages alongside an associated knowledge graph and employs a hybrid retriever combined with aggressive filtering to reduce retrieval latency. Experiments on multi-hop QA datasets demonstrate that \textGRIEVER outperforms conventional retrievers and shows strong potential as a base retriever within multi-step agentic frameworks.</abstract>
<identifier type="citekey">melo-etal-2025-dont</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.174/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2564</start>
<end>2572</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering
%A Melo, Andre
%A Chen, Enting
%A Vougiouklis, Pavlos
%A Diao, Chenxin
%A Piramanayagam, Shriram
%A Lai, Ruofei
%A Pan, Jeff Z.
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F melo-etal-2025-dont
%X Traditional Retrieval-augmented Generation systems struggle with complex multi-hop questions, which often require reasoning over multiple passages. While GraphRAG approaches address these challenges, most of them rely on expensive LLM calls. In this paper, we propose \textGRIEVER, a lightweight, low-resource, multi-step graph-based retriever for multi-hop QA. Unlike prior work, \textGRIEVER does not rely on LLMs and can perform multi-step retrieval in a few hundred milliseconds. It efficiently indexes passages alongside an associated knowledge graph and employs a hybrid retriever combined with aggressive filtering to reduce retrieval latency. Experiments on multi-hop QA datasets demonstrate that \textGRIEVER outperforms conventional retrievers and shows strong potential as a base retriever within multi-step agentic frameworks.
%U https://aclanthology.org/2025.emnlp-industry.174/
%P 2564-2572
Markdown (Informal)
[Don’t Forget the Base Retriever! A Low-Resource Graph-based Retriever for Multi-hop Question Answering](https://aclanthology.org/2025.emnlp-industry.174/) (Melo et al., EMNLP 2025)
ACL