@inproceedings{wu-luo-2026-toporag,
title = "{T}opo{RAG}: Graph-based {RAG} via Topology-aware Approximate Nearest Neighbor Search",
author = "Wu, Tianhao and
Luo, Siqiang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1703/",
pages = "34097--34108",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-augmented generation (RAG) has become a core technique for improving the factuality and reasoning ability of large language models. Recent efforts extend RAG with graph-structured knowledge, enhancing retrieval to capture relational context beyond isolated text chunks. However, many graph-based RAG systems rely on a two-stage pipeline: (i) classical approximate nearest neighbor (ANN) search to identify top-$k$ entities in the embedding space, (ii) heuristic neighbor expansion which augments the retrieved set by traversing immediate neighbors. This design underutilizes graph topology during retrieval and often introduces noisy or high-degree neighbors, leading to suboptimal evidence selection. In this paper, we propose TopoRAG, a retrieval framework that directly integrates structural constraints into ANN search via a diameter-constrained formulation. By selecting entities whose induced subgraph satisfies a diameter bound, TopoRAG enables topology-aware and noise-controlled graph retrieval. Experiments show that our approach consistently improves precision and significantly reduces context redundancy compared to existing methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-luo-2026-toporag">
<titleInfo>
<title>TopoRAG: Graph-based RAG via Topology-aware Approximate Nearest Neighbor Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianhao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqiang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Retrieval-augmented generation (RAG) has become a core technique for improving the factuality and reasoning ability of large language models. Recent efforts extend RAG with graph-structured knowledge, enhancing retrieval to capture relational context beyond isolated text chunks. However, many graph-based RAG systems rely on a two-stage pipeline: (i) classical approximate nearest neighbor (ANN) search to identify top-k entities in the embedding space, (ii) heuristic neighbor expansion which augments the retrieved set by traversing immediate neighbors. This design underutilizes graph topology during retrieval and often introduces noisy or high-degree neighbors, leading to suboptimal evidence selection. In this paper, we propose TopoRAG, a retrieval framework that directly integrates structural constraints into ANN search via a diameter-constrained formulation. By selecting entities whose induced subgraph satisfies a diameter bound, TopoRAG enables topology-aware and noise-controlled graph retrieval. Experiments show that our approach consistently improves precision and significantly reduces context redundancy compared to existing methods.</abstract>
<identifier type="citekey">wu-luo-2026-toporag</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1703/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34097</start>
<end>34108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TopoRAG: Graph-based RAG via Topology-aware Approximate Nearest Neighbor Search
%A Wu, Tianhao
%A Luo, Siqiang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wu-luo-2026-toporag
%X Retrieval-augmented generation (RAG) has become a core technique for improving the factuality and reasoning ability of large language models. Recent efforts extend RAG with graph-structured knowledge, enhancing retrieval to capture relational context beyond isolated text chunks. However, many graph-based RAG systems rely on a two-stage pipeline: (i) classical approximate nearest neighbor (ANN) search to identify top-k entities in the embedding space, (ii) heuristic neighbor expansion which augments the retrieved set by traversing immediate neighbors. This design underutilizes graph topology during retrieval and often introduces noisy or high-degree neighbors, leading to suboptimal evidence selection. In this paper, we propose TopoRAG, a retrieval framework that directly integrates structural constraints into ANN search via a diameter-constrained formulation. By selecting entities whose induced subgraph satisfies a diameter bound, TopoRAG enables topology-aware and noise-controlled graph retrieval. Experiments show that our approach consistently improves precision and significantly reduces context redundancy compared to existing methods.
%U https://aclanthology.org/2026.findings-acl.1703/
%P 34097-34108
Markdown (Informal)
[TopoRAG: Graph-based RAG via Topology-aware Approximate Nearest Neighbor Search](https://aclanthology.org/2026.findings-acl.1703/) (Wu & Luo, Findings 2026)
ACL