---
title: "Collision to Cognition — paper by Zhou et al. (2026)"
description: "The authors propose MeshRAG, which builds the retrieval graph using locality-sensitive hashing (LSH). 46 references."
authors: ["Chuang Zhou", "Zheng Yuan", "Linhao Luo", "Zhaozhuo Xu", "Yilin Xiao", "Junnan Dong", "Siyu An", "di Yin", "Xing Sun", "Xiao Huang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1156/"
doi: "10.18653/v1/2026.acl-long.1156"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhou-2026-collision-cognition-hash-driven-graph/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2026-collision-cognition-hash-driven-graph/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/) / Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG

# Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG

**Authors:** [Chuang Zhou](https://md.research.elamur.ai/free/en/authors/chuang-zhou/), [Zheng Yuan](https://md.research.elamur.ai/free/en/authors/zheng-yuan/), [Linhao Luo](https://md.research.elamur.ai/free/en/authors/linhao-luo/), [Zhaozhuo Xu](https://md.research.elamur.ai/free/en/authors/zhaozhuo-xu/), [Yilin Xiao](https://md.research.elamur.ai/free/en/authors/yilin-xiao/), [Junnan Dong](https://md.research.elamur.ai/free/en/authors/junnan-dong/), Siyu An, [di Yin](https://md.research.elamur.ai/free/en/authors/di-yin/), [Xing Sun](https://md.research.elamur.ai/free/en/authors/xing-sun/) and [Xiao Huang](https://md.research.elamur.ai/free/en/authors/xiao-xia-huang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1156/) · [PDF](https://aclanthology.org/2026.acl-long.1156.pdf) · [DOI 10.18653/v1/2026.acl-long.1156](https://doi.org/10.18653/v1/2026.acl-long.1156) · [OpenAlex](https://openalex.org/W7166814665)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
GraphRAG systems handle multi-hop questions better than flat dense retrieval, but building their graphs is costly. It typically depends on LLM calls for triple extraction or summarization, or on GPU-computed embeddings for clustering. Clustering also tends to place each passage in a single group. The authors propose MeshRAG, which builds the retrieval graph using locality-sensitive hashing (LSH). Entities are pulled from each chunk with regular expressions, and chunk similarity is approximated through MinHash signatures (an estimate of Jaccard overlap) indexed in banded LSH tables. Chunks that land in the same buckets become linked. Candidate buckets are kept or discarded using a BIC criterion under a Bernoulli model and then merged into larger communities. Because communities may overlap, one passage can belong to several topics. Retrieval then walks this two-level structure of chunks and communities. According to the authors, MeshRAG outperforms existing baselines and makes hash collisions available as traceable evidence for its decisions. Graph construction runs in minutes on CPU, with no LLM token or API cost.

## Key points
- The graph is built from bitwise hash operations only. More than ten thousand chunks can be structured in a few minutes, with no GPU and no API budget.
- Default settings are L = 8 LSH tables and MinHash signatures of length k = 12. Chunks can join several communities, unlike hard clustering methods such as K-means and DBSCAN.
- In the ablation, MeshRAG variants (1-hop and 2-hop, varying the number of communities) were more accurate than Dense Search, DBSCAN and K-means. The 1-hop, 5-community setting was chosen as the best balance of speed and accuracy.
- The method is robust to hyperparameters: when L and k vary, top-10 and top-20 retrieval overlap with the default stays above 0.90, and Spearman ρ and Kendall τ remain fairly high.
- The authors list three limitations: the method handles text only, graph search is iterative rather than FAISS-style single-shot, and lexical hashing misses synonyms. They suggest synonym normalization as a preprocessing fix for the last one.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 163 works · 21,032 citations
- [Monash University](https://md.research.elamur.ai/free/en/universities/monash-university/) — University, Melbourne, Australia · 64 works · 54,971 citations
- [Hong Kong Polytechnic University](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) — University, Hong Kong, China · 106 works · 5,190 citations
- [Stevens Institute of Technology](https://md.research.elamur.ai/free/en/universities/stevens-institute-of-technology/) — University, Hoboken, United States · 13 works · 95 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: 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. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhou2026collision,
  title = {{Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG}},
  author = {Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun and Xiao Huang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1156},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1156}
}
```

- [← previous COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values](https://md.research.elamur.ai/free/en/papers/wu-2026-coig-p-high-quality-large/)
- [next → Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks](https://md.research.elamur.ai/free/en/papers/hobbs-2026-collocational-bootstrapping-hypothesis-about-learning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/)

## References

46 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Muhammad Arslan, Hussam Ghanem, Saba Munawar, and Christophe Cruz. 2024. A survey on rag with llms. Procedia computer science, 246:3781–3790. [find](https://scholar.google.com/scholar?q=Muhammad+Arslan%2C+Hussam+Ghanem%2C+Saba+Munawar%2C+and+Christophe+Cruz%2E+2024%2E+A+survey+on+rag+with+llms%2E+Procedia+computer+science%2C+246%3A3781%E2%80%933790%2E)
3. Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao, and Xiao Huang. 2025. [You don’t need pre-built graphs for rag: Retrieval augmented generation with adaptive reasoning structures](https://md.research.elamur.ai/free/en/papers/chen-2025-don-t-need-pre-built/). arXiv preprint arXiv:2508.06105.
4. Shengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang, Zeyang Cui, Hao Chen, Yilin Xiao, Jiannong Cao, and Xiao Huang. 2026. [You don’t need pre-built graphs for rag: Retrieval augmented generation with adaptive reasoning structures](https://md.research.elamur.ai/free/en/papers/chen-2025-don-t-need-pre-built/). In Proceedings of the AAAI Conference on Artificial Intelligence,…
5. Flavio Chierichetti and Ravi Kumar. 2015. Lsh-preserving functions and their applications. Journal of the ACM (JACM), 62(5):1–25. [find](https://scholar.google.com/scholar?q=Flavio+Chierichetti+and+Ravi+Kumar%2E+2015%2E+Lsh%2Dpreserving+functions+and+their+applications%2E+Journal+of+the+ACM+%28JACM%29%2C+62%285%29%3A1%E2%80%9325%2E)
6. Tobias Christiani and Rasmus Pagh. 2017. Set similarity search beyond minhash. In Proceedings of the 49th annual ACM SIGACT symposium on theory of computing, pages 1094–1107. [find](https://scholar.google.com/scholar?q=Tobias+Christiani+and+Rasmus+Pagh%2E+2017%2E+Set+similarity+search+beyond+minhash%2E+In+Proceedings+of+the+49th+annual+ACM+SIGACT+symposium+on+theory+of+computing%2C+pages+1094%E2%80%931107%2E)
7. Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, and Fabrizio Silvestri. 2024. [The power of noise: Redefining retrieval for rag systems](https://md.research.elamur.ai/free/en/papers/cuconasu-2024-power-noise-redefining-retrieval-rag/). In Proceedings of the 47th International ACM SIGIR Conference on Research and Developm…
8. Biplob Debnath, Sudipta Sengupta, Jin Li, David J Lilja, and David HC Du. 2011. Bloomflash: Bloom filter on flash-based storage. In 2011 31st International Conference on Distributed Computing Systems, pages 635–644. IEEE. [find](https://scholar.google.com/scholar?q=Biplob+Debnath%2C+Sudipta+Sengupta%2C+Jin+Li%2C+David+J+Lilja%2C+and+David+HC+Du%2E+2011%2E+Bloomflash%3A+Bloom+filter+on+flash%2Dbased+storage%2E+In+2011+31st+International+Conference+on+Distributed+Computing+Systems%2C)
9. Junnan Dong, Siyu An, Yifei Yu, Qian-Wen Zhang, Linhao Luo, Xiao Huang, Yunsheng Wu, Di Yin, and Xing Sun. 2025. Youtu-graphrag: Vertically unified agents for graph retrieval-augmented complex reasoning. arXiv preprint arXiv:2508.19855. — [arXiv:2508.19855](https://arxiv.org/abs/2508.19855) [find](https://scholar.google.com/scholar?q=Junnan+Dong%2C+Siyu+An%2C+Yifei+Yu%2C+Qian%2DWen+Zhang%2C+Linhao+Luo%2C+Xiao+Huang%2C+Yunsheng+Wu%2C+Di+Yin%2C+and+Xing+Sun%2E+2025%2E+Youtu%2Dgraphrag%3A+Vertically+unified+agents+for+graph+retrieval%2Daugmented+complex+reasoni)
10. Junnan Dong, Qinggang Zhang, Chuang Zhou, Hao Chen, Daochen Zha, and Xiao Huang. 2024a. Cost-efficient knowledge-based question answering with large language models. Advances in Neural Information Processing Systems, 37:115261–115281. [find](https://scholar.google.com/scholar?q=Junnan+Dong%2C+Qinggang+Zhang%2C+Chuang+Zhou%2C+Hao+Chen%2C+Daochen+Zha%2C+and+Xiao+Huang%2E+2024a%2E+Cost%2Defficient+knowledge%2Dbased+question+answering+with+large+language+models%2E+Advances+in+Neural+Information+Pro)
11. Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, and Xiao Huang. 2024b. Modality-aware integration with large language models for knowledge-based visual question answering. In ACL, pages 2417–2429. ACL. [find](https://scholar.google.com/scholar?q=Junnan+Dong%2C+Qinggang+Zhang%2C+Huachi+Zhou%2C+Daochen+Zha%2C+Pai+Zheng%2C+and+Xiao+Huang%2E+2024b%2E+Modality%2Daware+integration+with+large+language+models+for+knowledge%2Dbased+visual+question+answering%2E+In+ACL%2C+pa)
12. Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Siyu An, Di Yin, Xing Sun, and Feiyue Huang. 2026. Deep tabular research via continual experience-driven execution. arXiv preprint arXiv:2603.09151. — [arXiv:2603.09151](https://arxiv.org/abs/2603.09151) [find](https://scholar.google.com/scholar?q=Junnan+Dong%2C+Chuang+Zhou%2C+Zheng+Yuan%2C+Yifei+Yu%2C+Siyu+An%2C+Di+Yin%2C+Xing+Sun%2C+and+Feiyue+Huang%2E+2026%2E+Deep+tabular+research+via+continual+experience%2Ddriven+execution%2E+arXiv+preprint+arXiv%3A2603%2E09151%2E+%E2%80%94+%5B)
13. Yuxin Dong, Shuo Wang, Hongye Zheng, Jiajing Chen, Zhenhong Zhang, and Chihang Wang. 2024c. Advanced rag models with graph structures: Optimizing complex knowledge reasoning and text generation. In 2024 5th International Symposium on Computer Engineering and Intelligent Communications (ISCEIC), page… [find](https://scholar.google.com/scholar?q=Yuxin+Dong%2C+Shuo+Wang%2C+Hongye+Zheng%2C+Jiajing+Chen%2C+Zhenhong+Zhang%2C+and+Chihang+Wang%2E+2024c%2E+Advanced+rag+models+with+graph+structures%3A+Optimizing+complex+knowledge+reasoning+and+text+generation%2E+In+20)
14. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+app)
15. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. [A survey on rag meeting llms: Towards retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/fan-2024-survey-rag-meeting-llms-towards/). In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 6491– 6501.
16. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2024. [Lightrag: Simple and fast retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/guo-2024-lightrag-simple-fast-retrieval-augmented/).
17. Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. [Hipporag: Neurobiologically inspired long-term memory for large language models](https://md.research.elamur.ai/free/en/papers/gutierrez-2024-hipporag-neurobiologically-inspired-long-term/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
18. Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, and Yu Su. 2025. [From rag to memory: Non-parametric continual learning for large language models](https://md.research.elamur.ai/free/en/papers/gutierrez-2025-rag-memory-non-parametric-continual/). arXiv preprint arXiv:2502.14802.
19. Haoyu Han, Li Ma, Harry Shomer, Yu Wang, Yongjia Lei, Kai Guo, Zhigang Hua, Bo Long, Hui Liu, Charu C Aggarwal, and 1 others. 2025. Rag vs. graphrag: A systematic evaluation and key insights. arXiv preprint arXiv:2502.11371. — [arXiv:2502.11371](https://arxiv.org/abs/2502.11371) [find](https://scholar.google.com/scholar?q=Haoyu+Han%2C+Li+Ma%2C+Harry+Shomer%2C+Yu+Wang%2C+Yongjia+Lei%2C+Kai+Guo%2C+Zhigang+Hua%2C+Bo+Long%2C+Hui+Liu%2C+Charu+C+Aggarwal%2C+and+1+others%2E+2025%2E+Rag+vs%2E+graphrag%3A+A+systematic+evaluation+and+key+insights%2E+arXiv+pr)
20. Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A Rossi, Subhabrata Mukherjee, Xianfeng Tang, and 1 others. 2024. [Retrieval-augmented generation with graphs (graphrag)](https://md.research.elamur.ai/free/en/papers/han-2025-retrieval-augmented-generation-graphs-graphrag/). arXiv preprint arXiv:2501.00309.
21. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. [G-retriever: Retrieval-augmented generation for textual graph understanding and question answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/). Advances in Neural Information Processing Systems, 37:132876–132907.
22. Luigi D Notarangelo, Min-Sung Kim, Jolan E Walter, and Yu Nee Lee. 2016. Human rag mutations: biochemistry and clinical implications. Nature Reviews Immunology, 16(4):234–246. [find](https://scholar.google.com/scholar?q=Luigi+D+Notarangelo%2C+Min%2DSung+Kim%2C+Jolan+E+Walter%2C+and+Yu+Nee+Lee%2E+2016%2E+Human+rag+mutations%3A+biochemistry+and+clinical+implications%2E+Nature+Reviews+Immunology%2C+16%284%29%3A234%E2%80%93246%2E)
23. Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D Manning. 2024. [Raptor: Recursive abstractive processing for tree-organized retrieval](https://md.research.elamur.ai/free/en/papers/sarthi-2024-raptor-recursive-abstractive-processing-tree/). In The Twelfth International Conference on Learning Representations.
24. Anshumali Shrivastava and Ping Li. 2014. In defense of minhash over simhash. In Artificial intelligence and statistics, pages 886–894. PMLR. [find](https://scholar.google.com/scholar?q=Anshumali+Shrivastava+and+Ping+Li%2E+2014%2E+In+defense+of+minhash+over+simhash%2E+In+Artificial+intelligence+and+statistics%2C+pages+886%E2%80%93894%2E+PMLR%2E)
25. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, and Suranga Nanayakkara. 2021. Fine-tune the entire rag architecture (including dpr retriever) for question-answering. arXiv preprint arXiv:2106.11517. — [arXiv:2106.11517](https://arxiv.org/abs/2106.11517) [find](https://scholar.google.com/scholar?q=Shamane+Siriwardhana%2C+Rivindu+Weerasekera%2C+Elliott+Wen%2C+and+Suranga+Nanayakkara%2E+2021%2E+Fine%2Dtune+the+entire+rag+architecture+%28including+dpr+retriever%29+for+question%2Danswering%2E+arXiv+preprint+arXiv%3A2106)
26. Sasu Tarkoma, Christian Esteve Rothenberg, and Eemil Lagerspetz. 2011. Theory and practice of bloom filters for distributed systems. IEEE Communications Surveys & Tutorials, 14(1):131–155. [find](https://scholar.google.com/scholar?q=Sasu+Tarkoma%2C+Christian+Esteve+Rothenberg%2C+and+Eemil+Lagerspetz%2E+2011%2E+Theory+and+practice+of+bloom+filters+for+distributed+systems%2E+IEEE+Communications+Surveys+%26+Tutorials%2C+14%281%29%3A131%E2%80%93155%2E)
27. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, and 1 others. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
28. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. 9835 musique: Multi-hop questions via single-hop question composition. Trans. Assoc. Comput. Linguistics, 10:539–554. [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+9835+musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Trans%2E+Assoc%2E+Comput%2E+Linguistics%2C+10%3A539%E2%80%93554%2E)
29. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). arXiv preprint arXiv:2011.01060.
30. Yu Wang, Nedim Lipka, Ryan A Rossi, Alexa Siu, Ruiyi Zhang, and Tyler Derr. 2024. Knowledge graph prompting for multi-document question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19206–19214. [find](https://scholar.google.com/scholar?q=Yu+Wang%2C+Nedim+Lipka%2C+Ryan+A+Rossi%2C+Alexa+Siu%2C+Ruiyi+Zhang%2C+and+Tyler+Derr%2E+2024%2E+Knowledge+graph+prompting+for+multi%2Ddocument+question+answering%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+I)
31. Omid Jafari, Preeti Maurya, Parth Nagarkar, Khandker Mushfiqul Islam, and Chidambaram Crushev. 2021. A survey on locality sensitive hashing algorithms and their applications. arXiv preprint arXiv:2102.08942. — [arXiv:2102.08942](https://arxiv.org/abs/2102.08942) [find](https://scholar.google.com/scholar?q=Omid+Jafari%2C+Preeti+Maurya%2C+Parth+Nagarkar%2C+Khandker+Mushfiqul+Islam%2C+and+Chidambaram+Crushev%2E+2021%2E+A+survey+on+locality+sensitive+hashing+algorithms+and+their+applications%2E+arXiv+preprint+arXiv%3A2102)
32. Xian Wu, Moses Charikar, and Vishnu Natchu. 2018. Local density estimation in high dimensions. In International Conference on Machine Learning, pages 5296–5305. PMLR. [find](https://scholar.google.com/scholar?q=Xian+Wu%2C+Moses+Charikar%2C+and+Vishnu+Natchu%2E+2018%2E+Local+density+estimation+in+high+dimensions%2E+In+International+Conference+on+Machine+Learning%2C+pages+5296%E2%80%935305%2E+PMLR%2E)
33. Jouni Kuha. 2004. Aic and bic: Comparisons of assumptions and performance. Sociological methods & research, 33(2):188–229. [find](https://scholar.google.com/scholar?q=Jouni+Kuha%2E+2004%2E+Aic+and+bic%3A+Comparisons+of+assumptions+and+performance%2E+Sociological+methods+%26+research%2C+33%282%29%3A188%E2%80%93229%2E)
34. Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, and Xiao Huang. 2026a. [Logicpoison: Logical attacks on graph retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/xiao-2026-logicpoison-logical-attacks-graph-retrieval/). arXiv preprint arXiv:2604.02954.
35. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
36. Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Dinh Phung, Chen Gong, and Shirui Pan. 2025. Gfm-rag: Graph foundation model for retrieval augmented generation. arXiv preprint arXiv:2502.01113. — [arXiv:2502.01113](https://arxiv.org/abs/2502.01113) [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Zicheng+Zhao%2C+Gholamreza+Haffari%2C+Dinh+Phung%2C+Chen+Gong%2C+and+Shirui+Pan%2E+2025%2E+Gfm%2Drag%3A+Graph+foundation+model+for+retrieval+augmented+generation%2E+arXiv+preprint+arXiv%3A2502%2E01113%2E+%E2%80%94+%5BarXiv)
37. Yilin Xiao, Junnan Dong, Chuang Zhou, Su Dong, Qianwen Zhang, Di Yin, Xing Sun, and Xiao Huang. 2025. Graphrag-bench: Challenging domain-specific reasoning for evaluating graph retrieval-augmented generation. arXiv preprint arXiv:2506.02404. — [arXiv:2506.02404](https://arxiv.org/abs/2506.02404) [find](https://scholar.google.com/scholar?q=Yilin+Xiao%2C+Junnan+Dong%2C+Chuang+Zhou%2C+Su+Dong%2C+Qianwen+Zhang%2C+Di+Yin%2C+Xing+Sun%2C+and+Xiao+Huang%2E+2025%2E+Graphrag%2Dbench%3A+Challenging+domain%2Dspecific+reasoning+for+evaluating+graph+retrieval%2Daugmented+gen)
38. Yilin Xiao, Chuang Zhou, Qinggang Zhang, Bo Li, Qing Li, and Xiao Huang. 2026b. Reliable reasoning path: Distilling effective guidance for llm reasoning with knowledge graphs. IEEE Transactions on Knowledge and Data Engineering. [find](https://scholar.google.com/scholar?q=Yilin+Xiao%2C+Chuang+Zhou%2C+Qinggang+Zhang%2C+Bo+Li%2C+Qing+Li%2C+and+Xiao+Huang%2E+2026b%2E+Reliable+reasoning+path%3A+Distilling+effective+guidance+for+llm+reasoning+with+knowledge+graphs%2E+IEEE+Transactions+on+Kno)
39. Chang Yang, Chuang Zhou, Yilin Xiao, Su Dong, Luyao Zhuang, Yujing Zhang, Zhu Wang, Zijin Hong, Zheng Yuan, Zhishang Xiang, and 1 others. 2026. Graph-based agent memory: Taxonomy, techniques, and applications. arXiv preprint arXiv:2602.05665. — [arXiv:2602.05665](https://arxiv.org/abs/2602.05665) [find](https://scholar.google.com/scholar?q=Chang+Yang%2C+Chuang+Zhou%2C+Yilin+Xiao%2C+Su+Dong%2C+Luyao+Zhuang%2C+Yujing+Zhang%2C+Zhu+Wang%2C+Zijin+Hong%2C+Zheng+Yuan%2C+Zhishang+Xiang%2C+and+1+others%2E+2026%2E+Graph%2Dbased+agent+memory%3A+Taxonomy%2C+techniques%2C+and+appl)
40. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). arXiv preprint arXiv:1809.09600.
41. Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, Zheng Yuan, Huachi Zhou, Zijin Hong, Hao Chen, Yilin Xiao, Chuang Zhou, Junnan Dong, and 1 others. 2025. [A survey of graph retrieval-augmented generation for customized large language models](https://md.research.elamur.ai/free/en/papers/zhang-2025-survey-graph-retrieval-augmented-generation/). arXiv preprint arXiv:2501.13958.
42. Yibo Zhao, Jiapeng Zhu, Ye Guo, Kangkang He, and Xiang Li. 2025. Eˆ 2graphrag: Streamlining graph-based rag for high efficiency and effectiveness. arXiv preprint arXiv:2505.24226. — [arXiv:2505.24226](https://arxiv.org/abs/2505.24226) [find](https://scholar.google.com/scholar?q=Yibo+Zhao%2C+Jiapeng+Zhu%2C+Ye+Guo%2C+Kangkang+He%2C+and+Xiang+Li%2E+2025%2E+E%CB%86+2graphrag%3A+Streamlining+graph%2Dbased+rag+for+high+efficiency+and+effectiveness%2E+arXiv+preprint+arXiv%3A2505%2E24226%2E+%E2%80%94+%5BarXiv%3A2505%2E24226%5D)
43. Chuang Zhou, Junnan Dong, Xiao Huang, Zirui Liu, Kaixiong Zhou, and Zhaozhuo Xu. 2024. Quest: Efficient extreme multi-label text classification with large language models on commodity hardware. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3929–3940. [find](https://scholar.google.com/scholar?q=Chuang+Zhou%2C+Junnan+Dong%2C+Xiao+Huang%2C+Zirui+Liu%2C+Kaixiong+Zhou%2C+and+Zhaozhuo+Xu%2E+2024%2E+Quest%3A+Efficient+extreme+multi%2Dlabel+text+classification+with+large+language+models+on+commodity+hardware%2E+In+Fin)
44. Chuang Zhou, Jiahe Du, Huachi Zhou, Hao Chen, Feiran Huang, and Xiao Huang. 2025a. [Text-attributed graph learning with coupled augmentations](https://md.research.elamur.ai/free/en/papers/zhou-2025-text-attributed-graph-learning-coupled/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 10865–10876.
45. Chuang Zhou, Zhu Wang, Shengyuan Chen, Jiahe Du, Qiyuan Zheng, Zhaozhuo Xu, and Xiao Huang. 2025b. [Taming language models for text-attributed graph learning with decoupled aggregation](https://md.research.elamur.ai/free/en/papers/zhou-2025-taming-language-models-text-attributed/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
46. Yinghao Zhu, Changyu Ren, Shiyun Xie, Shukai Liu, Hangyuan Ji, Zixiang Wang, Tao Sun, Long He, Zhoujun Li, Xi Zhu, and 1 others. 2024. Realm: Rag-driven enhancement of multimodal electronic health records analysis via large language models. arXiv preprint arXiv:2402.07016. — [arXiv:2402.07016](https://arxiv.org/abs/2402.07016) [find](https://scholar.google.com/scholar?q=Yinghao+Zhu%2C+Changyu+Ren%2C+Shiyun+Xie%2C+Shukai+Liu%2C+Hangyuan+Ji%2C+Zixiang+Wang%2C+Tao+Sun%2C+Long+He%2C+Zhoujun+Li%2C+Xi+Zhu%2C+and+1+others%2E+2024%2E+Realm%3A+Rag%2Ddriven+enhancement+of+multimodal+electronic+health+rec)

*Updated 2 November 2026*