@inproceedings{zhou-etal-2026-collision,
title = "Collision to Cognition: Hash-Driven Graph Construction for Efficient {RAG}",
author = "Zhou, Chuang and
Yuan, Zheng and
Luo, Linhao and
Xu, Zhaozhuo and
Xiao, Yilin and
Dong, Junnan and
An, Siyu and
Yin, di and
Sun, Xing and
Huang, Xiao",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1156/",
pages = "25224--25240",
ISBN = "979-8-89176-390-6",
abstract = "Retrieval-Augmented Generation (RAG) has long been a promising paradigm for enhancing large language models (LLMs) with external knowledge. Traditional embedding-based methods for graph construction can capture semantic similarity but struggle to establish fine-grained, interpretable logical relationships. Recently, Graph-enhanced RAG (GraphRAG) has gained increasing popularity for its capability in modeling logical relationships. However, graph construction requires extensive token consumption for triple extraction and summarization, making it costly and slow. Accordingly, we propose MeshRAG, a novel framework for mining efficient structures via hashing to enhance RAG. We adopt an inductive paradigm in which global graph structure emerges from local hash collisions rather than explicit symbolic extraction. By replacing neural embedding search with lightweight and bitwise operations, MeshRAG automates a simple and rapid graph construction process. Furthermore, the hash collision mechanism provides transparent evidence for logical connections and retrieval decisions. Experimental results show that MeshRAG outperforms existing baselines, while its graph construction requires no GPU resources or token budget and can structure over ten thousand chunks in a few minutes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-collision">
<titleInfo>
<title>Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linhao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaozhuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilin</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">di</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Huang</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) has long been a promising paradigm for enhancing large language models (LLMs) with external knowledge. Traditional embedding-based methods for graph construction can capture semantic similarity but struggle to establish fine-grained, interpretable logical relationships. Recently, Graph-enhanced RAG (GraphRAG) has gained increasing popularity for its capability in modeling logical relationships. However, graph construction requires extensive token consumption for triple extraction and summarization, making it costly and slow. Accordingly, we propose MeshRAG, a novel framework for mining efficient structures via hashing to enhance RAG. We adopt an inductive paradigm in which global graph structure emerges from local hash collisions rather than explicit symbolic extraction. By replacing neural embedding search with lightweight and bitwise operations, MeshRAG automates a simple and rapid graph construction process. Furthermore, the hash collision mechanism provides transparent evidence for logical connections and retrieval decisions. Experimental results show that MeshRAG outperforms existing baselines, while its graph construction requires no GPU resources or token budget and can structure over ten thousand chunks in a few minutes.</abstract>
<identifier type="citekey">zhou-etal-2026-collision</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1156/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>25224</start>
<end>25240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG
%A Zhou, Chuang
%A Yuan, Zheng
%A Luo, Linhao
%A Xu, Zhaozhuo
%A Xiao, Yilin
%A Dong, Junnan
%A An, Siyu
%A Yin, di
%A Sun, Xing
%A Huang, Xiao
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F zhou-etal-2026-collision
%X Retrieval-Augmented Generation (RAG) has long been a promising paradigm for enhancing large language models (LLMs) with external knowledge. Traditional embedding-based methods for graph construction can capture semantic similarity but struggle to establish fine-grained, interpretable logical relationships. Recently, Graph-enhanced RAG (GraphRAG) has gained increasing popularity for its capability in modeling logical relationships. However, graph construction requires extensive token consumption for triple extraction and summarization, making it costly and slow. Accordingly, we propose MeshRAG, a novel framework for mining efficient structures via hashing to enhance RAG. We adopt an inductive paradigm in which global graph structure emerges from local hash collisions rather than explicit symbolic extraction. By replacing neural embedding search with lightweight and bitwise operations, MeshRAG automates a simple and rapid graph construction process. Furthermore, the hash collision mechanism provides transparent evidence for logical connections and retrieval decisions. Experimental results show that MeshRAG outperforms existing baselines, while its graph construction requires no GPU resources or token budget and can structure over ten thousand chunks in a few minutes.
%U https://aclanthology.org/2026.acl-long.1156/
%P 25224-25240
Markdown (Informal)
[Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG](https://aclanthology.org/2026.acl-long.1156/) (Zhou et al., ACL 2026)
ACL
- Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, and Xiao Huang. 2026. Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25224–25240, San Diego, California, United States. Association for Computational Linguistics.