---
title: "Mix-of-Granularity — paper by Zhong et al. (2025)"
description: "The authors propose Mix-of-Granularity (MoG), which borrows the routing idea from Mix-of-Experts. 56 references, cited by 10 papers here."
authors: ["Zijie Zhong", "Hanwen Liu", "Xiaoya Cui", "Xiaofan Zhang", "Zengchang Qin"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.384/"
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/zhong-2025-mix-granularity-optimize-chunking-granularity/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhong-2025-mix-granularity-optimize-chunking-granularity/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/7/) / Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

# Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

**Authors:** Zijie Zhong, Hanwen Liu, Xiaoya Cui, [Xiaofan Zhang](https://md.research.elamur.ai/free/en/authors/xiaofan-zhang/) and Zengchang Qin · **Year:** 2025 · **Venue:** [Proceedings of the 31st International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/2025/)) · **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/2025.coling-main.384/) · [PDF](https://aclanthology.org/2025.coling-main.384.pdf) · [OpenAlex](https://openalex.org/W4399356589)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [10](https://md.research.elamur.ai/free/en/papers/zhong-2025-mix-granularity-optimize-chunking-granularity/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
RAG systems usually split their reference collections into chunks of one fixed size. That size is hard to tune, because knowledge sources differ in structure and information density, and individual questions range from narrow to broad. The authors propose Mix-of-Granularity (MoG), which borrows the routing idea from Mix-of-Experts. Each corpus is pre-chunked at several nested granularity levels. A router reads the RoBERTa-encoded query and assigns weights that decide which granularity's BM25-ranked snippets get priority.

The router is hard to train directly, since top-k snippet selection blocks backpropagation. The authors work around this with a loss built on soft labels, which are approximate targets produced offline by TF-IDF or RoBERTa. They also introduce MoG-Graph (MoGG), which turns reference documents into a graph so that related but far-apart passages can be retrieved together via neighbour hops.

On medical question answering, both methods generally beat MedRAG and chain-of-thought baselines across several LLMs. MoGG gains more while training on a much smaller corpus. The work matters because it replaces manual chunk-size tuning with a learned, query-dependent choice.

## Key points
- Chunking is non-overlapping and hierarchical. In the illustrated setup there are 5 granularity levels, and each coarser chunk merges two adjacent chunks from the level below.
- Evaluation covers medical QA (about 7,000 questions) using the MedCorp, Textbooks and StatPearls corpora. Backbone LLMs include GPT-3.5, GLM3, InternLM, Llama3 and Qwen1.5.
- On smaller models, MoG improves accuracy by about 5% on average over MedRAG and 8.7% over CoT.
- MoGG was trained on Textbooks, which holds only about 0.2% of MedCorp's snippets. Even so, it yields a larger average gain over MedRAG than MoG does.
- Storing one corpus copy plus five embedding sets takes about 2.7× the original corpus size. Adding granularity levels raises inference time only marginally.
- Stated limitations:
  - Granularity levels are set by hand.
  - The router uses only query semantics.
  - A compromised router could steer retrieval toward malicious sources.

*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

- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 152 works · 13,164 citations
- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations

📚 Shelves (6): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang and Zengchang Qin. 2025. Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation. Proceedings of the 31st International Conference on Computational Linguistics.

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

```bibtex
@inproceedings{zhong2025mix,
  title = {{Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation}},
  author = {Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang and Zengchang Qin},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.384/}
}
```

- [← previous Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/yu-2025-long-short-chain-thought-mixture/)
- [next → Natural Language Processing RELIES on Linguistics](https://md.research.elamur.ai/free/en/papers/opitz-2025-natural-language-processing-relies-linguistics/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/7/)

## References

56 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yu, Jing Yu, Yuhang Zang, Chuyu Zhang, Li Zhang, Pan Zhang, Peng Zhang, Ruijie Zhang, Shuo Zhang, Songyang Zhang, Wenjian Zhang, Wenwei Zhang, Xingcheng Zhang, Xinyue Zhang, Hui Zhao, Qian Zhao, Xiaomeng Zhao, Fengzhe Zhou, Zaida Zhou, Jingming Zhuo, Yicheng Zou, Xipeng Qiu, Yu Qiao, and Dahua Lin.… — [InternLM2 Technical Report](https://md.research.elamur.ai/free/en/papers/cai-2024-internlm2-technical-report/)
2. Meta AI. 2024. Introducing meta llama 3: The most capable openly available llm to date. Meta document. [find](https://scholar.google.com/scholar?q=Meta+AI%2E+2024%2E+Introducing+meta+llama+3%3A+The+most+capable+openly+available+llm+to+date%2E+Meta+document%2E)
3. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, P… — [Qwen Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/)
4. Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cas… [find](https://scholar.google.com/scholar?q=Sebastian+Borgeaud%2C+Arthur+Mensch%2C+Jordan+Hoffmann%2C+Trevor+Cai%2C+Eliza+Rutherford%2C+Katie+Millican%2C+George+van+den+Driessche%2C+Jean%2DBaptiste+Lespiau%2C+Bogdan+Damoc%2C+Aidan+Clark%2C+Diego+de+Las+Casas%2C+Aureli)
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
6. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, Aijia Guo, Qipeng Guo, Conghui He, Yingfan Hu, Ting Huang, Tao Jiang, Penglong Jiao, Zhenjia… [find](https://scholar.google.com/scholar?q=Zheng+Cai%2C+Maosong+Cao%2C+Haojiong+Chen%2C+Kai+Chen%2C+Keyu+Chen%2C+Xin+Chen%2C+Xun+Chen%2C+Zehui+Chen%2C+Zhi+Chen%2C+Pei+Chu%2C+Xiaoyi+Dong%2C+Haodong+Duan%2C+Qi+Fan%2C+Zhaoye+Fei%2C+Yang+Gao%2C+Jiaye+Ge%2C+Chenya+Gu%2C+Yuzhe+Gu%2C+T)
7. Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. 2020. [Specter: Document-level representation learning using citation-informed transformers](https://md.research.elamur.ai/free/en/papers/cohan-2020-specter-document-level-representation-learning/). Preprint, arXiv:2004.07180.
8. Neo4j Company. 2012. Neo4j - the world’s leading graph database. [find](https://scholar.google.com/scholar?q=Neo4j+Company%2E+2012%2E+Neo4j+%2D+the+world%E2%80%99s+leading+graph+database%2E)
9. Gordon V Cormack, Charles LA Clarke, and Stefan Buettcher. 2009. [Reciprocal rank fusion outperforms condorcet and individual rank learning methods](https://md.research.elamur.ai/free/en/papers/cormack-2009-reciprocal-rank-fusion-outperforms/). In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 758–759.
10. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, Lei Li, and Zhifang Sui. 2023. [A survey on in-context learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/). Preprint, arXiv:2301.00234.
11. Zhe Dong, Jianmo Ni, Daniel M. Bikel, Enrique Alfonseca, Yuan Wang, Chen Qu, and Imed Zitouni. 2022. Exploring dual encoder architectures for question answering. Preprint, arXiv:2204.07120. [find](https://scholar.google.com/scholar?q=Zhe+Dong%2C+Jianmo+Ni%2C+Daniel+M%2E+Bikel%2C+Enrique+Alfonseca%2C+Yuan+Wang%2C+Chen+Qu%2C+and+Imed+Zitouni%2E+2022%2E+Exploring+dual+encoder+architectures+for+question+answering%2E+Preprint%2C+arXiv%3A2204%2E07120%2E)
12. Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2022. [Glm: General language model pretraining with autoregressive blank infilling](https://md.research.elamur.ai/free/en/papers/du-2022-glm-general-language-model-pretraining/). Preprint, arXiv:2103.10360.
13. Lise Getoor Galileo Mark Namata, Ben London and Bert Huang. 2012. Query-driven active surveying for collective classification. In International Workshop on Mining and Learning with Graphs, Edinburgh, Scotland. [find](https://scholar.google.com/scholar?q=Lise+Getoor+Galileo+Mark+Namata%2C+Ben+London+and+Bert+Huang%2E+2012%2E+Query%2Ddriven+active+surveying+for+collective+classification%2E+In+International+Workshop+on+Mining+and+Learning+with+Graphs%2C+Edinburgh%2C+)
14. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997.
15. Qipeng Guo, Zhijing Jin, Xipeng Qiu, Weinan Zhang, David Wipf, and Zheng Zhang. 2020. Cyclegt: Unsupervised graph-to-text and text-to-graph generation via cycle training. Preprint, arXiv:2006.04702. [find](https://scholar.google.com/scholar?q=Qipeng+Guo%2C+Zhijing+Jin%2C+Xipeng+Qiu%2C+Weinan+Zhang%2C+David+Wipf%2C+and+Zheng+Zhang%2E+2020%2E+Cyclegt%3A+Unsupervised+graph%2Dto%2Dtext+and+text%2Dto%2Dgraph+generation+via+cycle+training%2E+Preprint%2C+arXiv%3A2006%2E04702%2E)
16. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Preprint, arXiv:2009.03300.
17. Daniel Scott Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, and Sergio E Baranzini. 2017. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife, 6:e26726. [find](https://scholar.google.com/scholar?q=Daniel+Scott+Himmelstein%2C+Antoine+Lizee%2C+Christine+Hessler%2C+Leo+Brueggeman%2C+Sabrina+L+Chen%2C+Dexter+Hadley%2C+Ari+Green%2C+Pouya+Khankhanian%2C+and+Sergio+E+Baranzini%2E+2017%2E+Systematic+integration+of+biomedi)
18. Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi, Kevin Chen-Chuan Chang, and Bryan Catanzaro. 2024. Raven: In-context learning with retrieval-augmented encoder-decoder language models. Preprint, arXiv:2308.07922. — [arXiv:2308.07922](https://arxiv.org/abs/2308.07922) [find](https://scholar.google.com/scholar?q=Jie+Huang%2C+Wei+Ping%2C+Peng+Xu%2C+Mohammad+Shoeybi%2C+Kevin+Chen%2DChuan+Chang%2C+and+Bryan+Catanzaro%2E+2024%2E+Raven%3A+In%2Dcontext+learning+with+retrieval%2Daugmented+encoder%2Ddecoder+language+models%2E+Preprint%2C+arXiv%3A)
19. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022a. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/). Preprint, arXiv:2112.09118.
20. Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022b. [Atlas: Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). Preprint, arXiv:2208.03299.
21. Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). Preprint, arXiv:2305.06983.
22. Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2020. [What disease does this patient have? a large-scale open domain question answering dataset from medical exams](https://md.research.elamur.ai/free/en/papers/jin-2020-disease-this-patient-have-large/). Preprint, arXiv:2009.13081.
23. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W. Cohen, and Xinghua Lu. 2019. [Pubmedqa: A dataset for biomedical research question answering](https://md.research.elamur.ai/free/en/papers/jin-2019-pubmedqa-dataset-biomedical-research-question/). Preprint, arXiv:1909.06146.
24. Qiao Jin, Won Kim, Qingyu Chen, Donald C Comeau, Lana Yeganova, W John Wilbur, and Zhiyong Lu. 2023. Medcpt: Contrastive pre-trained transformers with large-scale pubmed search logs for zero-shot biomedical information retrieval. Bioinformatics, 39(11). [find](https://scholar.google.com/scholar?q=Qiao+Jin%2C+Won+Kim%2C+Qingyu+Chen%2C+Donald+C+Comeau%2C+Lana+Yeganova%2C+W+John+Wilbur%2C+and+Zhiyong+Lu%2E+2023%2E+Medcpt%3A+Contrastive+pre%2Dtrained+transformers+with+large%2Dscale+pubmed+search+logs+for+zero%2Dshot+biom)
25. Assia Khan. 2023. Retrieval augmented generation: 5 uses and their examples. Lettria. [find](https://scholar.google.com/scholar?q=Assia+Khan%2E+2023%2E+Retrieval+augmented+generation%3A+5+uses+and+their+examples%2E+Lettria%2E)
26. Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2020. Generalization through memorization: Nearest neighbor language models. Preprint, arXiv:1911.00172. [find](https://scholar.google.com/scholar?q=Urvashi+Khandelwal%2C+Omer+Levy%2C+Dan+Jurafsky%2C+Luke+Zettlemoyer%2C+and+Mike+Lewis%2E+2020%2E+Generalization+through+memorization%3A+Nearest+neighbor+language+models%2E+Preprint%2C+arXiv%3A1911%2E00172%2E)
27. Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, and Matei Zaharia. 2023. [Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive nlp](https://md.research.elamur.ai/free/en/papers/khattab-2022-demonstrate-search-predict-composing-retrieval/). Preprint, arXiv:2212.14024.
28. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Proc…
29. Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu, and Lan Xu. 2024. Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision. [find](https://scholar.google.com/scholar?q=Han+Liang%2C+Wenqian+Zhang%2C+Wenxuan+Li%2C+Jingyi+Yu%2C+and+Lan+Xu%2E+2024%2E+Intergen%3A+Diffusion%2Dbased+multi%2Dhuman+motion+generation+under+complex+interactions%2E+International+Journal+of+Computer+Vision%2E)
30. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). Preprint, arXiv:1907.11692.
31. Igor Melnyk, Pierre Dognin, and Payel Das. 2022. Knowledge graph generation from text. Preprint, arXiv:2211.10511. [find](https://scholar.google.com/scholar?q=Igor+Melnyk%2C+Pierre+Dognin%2C+and+Payel+Das%2E+2022%2E+Knowledge+graph+generation+from+text%2E+Preprint%2C+arXiv%3A2211%2E10511%2E)
32. Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, and Isao Echizen. 2022. Ease: Entity-aware contrastive learning of sentence embedding. Preprint, arXiv:2205.04260. [find](https://scholar.google.com/scholar?q=Sosuke+Nishikawa%2C+Ryokan+Ri%2C+Ikuya+Yamada%2C+Yoshimasa+Tsuruoka%2C+and+Isao+Echizen%2E+2022%2E+Ease%3A+Entity%2Daware+contrastive+learning+of+sentence+embedding%2E+Preprint%2C+arXiv%3A2205%2E04260%2E)
33. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. [Medmcqa : A large-scale multi-subject multi-choice dataset for medical domain question answering](https://md.research.elamur.ai/free/en/papers/pal-2022-medmcqa-large-scale-multi-subject/). Preprint, arXiv:2203.14371.
34. Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2017. [Billion-scale similarity search with gpus](https://md.research.elamur.ai/free/en/papers/johnson-2017-billion-scale-similarity-search-gpus/). Preprint, arXiv:1702.08734.
35. StatPearls Publishing. 2024. Statpearls. Treasure Island (FL): StatPearls Publishing. Available from: [https://www.ncbi.nlm.nih.gov/books/NBK430685/](https://www.ncbi.nlm.nih.gov/books/NBK430685/). [↗](https://www.ncbi.nlm.nih.gov/books/NBK430685/)
36. Minki Kang, Jin Myung Kwak, Jinheon Baek, and Sung Ju Hwang. 2023. [Knowledge graph-augmented language models for knowledge-grounded dialogue generation](https://md.research.elamur.ai/free/en/papers/kang-2023-knowledge-graph-augmented-language-models/). Preprint, arXiv:2305.18846.
37. Irina Radeva, Ivan Popchev, Lyubka Doukovska, and Miroslava Dimitrova. 2024. Web application for retrieval-augmented generation: Implementation and testing. Electronics, 13:1361. [find](https://scholar.google.com/scholar?q=Irina+Radeva%2C+Ivan+Popchev%2C+Lyubka+Doukovska%2C+and+Miroslava+Dimitrova%2E+2024%2E+Web+application+for+retrieval%2Daugmented+generation%3A+Implementation+and+testing%2E+Electronics%2C+13%3A1361%2E)
38. YuHe Ke, Liyuan Jin, Kabilan Elangovan, Hairil Rizal Abdullah, Nan Liu, Alex Tiong Heng Sia, Chai Rick Soh, Joshua Yi Min Tung, Jasmine Chiat Ling Ong, and Daniel Shu Wei Ting. 2024. Development and testing of retrieval augmented generation in large language models – a case study report. Preprint, a… — [arXiv:2402.01733](https://arxiv.org/abs/2402.01733) [find](https://scholar.google.com/scholar?q=YuHe+Ke%2C+Liyuan+Jin%2C+Kabilan+Elangovan%2C+Hairil+Rizal+Abdullah%2C+Nan+Liu%2C+Alex+Tiong+Heng+Sia%2C+Chai+Rick+Soh%2C+Joshua+Yi+Min+Tung%2C+Jasmine+Chiat+Ling+Ong%2C+and+Daniel+Shu+Wei+Ting%2E+2024%2E+Development+and+t)
39. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). Preprint, arXiv:2302.00083.
40. Juan Enrique Ramos. 2003. Using TF-IDF to determine word relevance in document queries. [find](https://scholar.google.com/scholar?q=Juan+Enrique+Ramos%2E+2003%2E+Using+TF%2DIDF+to+determine+word+relevance+in+document+queries%2E)
41. Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+Robertson+and+Hugo+Zaragoza%2E+2009%2E+The+probabilistic+relevance+framework%3A+Bm25+and+beyond%2E+Found%2E+Trends+Inf%2E+Retr%2E%2C+3%284%29%3A333%E2%80%93389%2E)
42. Wikimedia Foundation. 2024. Wikipedia. The Free Encyclopedia. Available from: [https://www.wikipedia.org](https://www.wikipedia.org). [↗](https://www.wikipedia.org)
43. Krystian Safjan. 2023. From fixed-size to nlp chunking -a deep dive into text chunking techniques. Krystian’s Safjan Blog. [find](https://scholar.google.com/scholar?q=Krystian+Safjan%2E+2023%2E+From+fixed%2Dsize+to+nlp+chunking+%2Da+deep+dive+into+text+chunking+techniques%2E+Krystian%E2%80%99s+Safjan+Blog%2E)
44. Guangzhi Xiong, Qiao Jin, Zhiyong Lu, and Aidong Zhang. 2024. [Benchmarking retrieval-augmented generation for medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/). Preprint, arXiv:2402.13178.
45. 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/). Preprint, arXiv:2401.18059.
46. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen tau Yih. 2023. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). Preprint, arXiv:2301.12652.
47. Jiaxuan You, Rex Ying, Xiang Ren, William L. Hamilton, and Jure Leskovec. 2018. Graphrnn: Generating realistic graphs with deep auto-regressive models. Preprint, arXiv:1802.08773. [find](https://scholar.google.com/scholar?q=Jiaxuan+You%2C+Rex+Ying%2C+Xiang+Ren%2C+William+L%2E+Hamilton%2C+and+Jure+Leskovec%2E+2018%2E+Graphrnn%3A+Generating+realistic+graphs+with+deep+auto%2Dregressive+models%2E+Preprint%2C+arXiv%3A1802%2E08773%2E)
48. Xiao Zhang, Ji Wu, Zhiyang He, Xien Liu, and Ying Su. 2018. Medical exam question answering with large-scale reading comprehension. Preprint, arXiv:1802.10279. — [arXiv:1802.10279](https://arxiv.org/abs/1802.10279) [find](https://scholar.google.com/scholar?q=Xiao+Zhang%2C+Ji+Wu%2C+Zhiyang+He%2C+Xien+Liu%2C+and+Ying+Su%2E+2018%2E+Medical+exam+question+answering+with+large%2Dscale+reading+comprehension%2E+Preprint%2C+arXiv%3A1802%2E10279%2E+%E2%80%94+%5BarXiv%3A1802%2E10279%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
49. Ryan Siegler. 2024. Optimizing vector search with metadata filtering. KX systems. [find](https://scholar.google.com/scholar?q=Ryan+Siegler%2E+2024%2E+Optimizing+vector+search+with+metadata+filtering%2E+KX+systems%2E)
50. Sumit Soman and Sujoy Roychowdhury. 2024. Observations on building rag systems for technical documents. Preprint, arXiv:2404.00657. — [arXiv:2404.00657](https://arxiv.org/abs/2404.00657) [find](https://scholar.google.com/scholar?q=Sumit+Soman+and+Sujoy+Roychowdhury%2E+2024%2E+Observations+on+building+rag+systems+for+technical+documents%2E+Preprint%2C+arXiv%3A2404%2E00657%2E+%E2%80%94+%5BarXiv%3A2404%2E00657%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2404%2E00657%29)
51. Antematter team. 2024. Optimizing retrieval-augmented generation with advanced chunking techniques: A comparative study. Antematter. [find](https://scholar.google.com/scholar?q=Antematter+team%2E+2024%2E+Optimizing+retrieval%2Daugmented+generation+with+advanced+chunking+techniques%3A+A+comparative+study%2E+Antematter%2E)
52. LangChain team. 2023. Parent document retriever. LangChain document. [find](https://scholar.google.com/scholar?q=LangChain+team%2E+2023%2E+Parent+document+retriever%2E+LangChain+document%2E)
53. George Tsatsaronis, Georgios Balikas, Prodromos Malakasiotis, Ioannis Partalas, Matthias Zschunke, Michael Alvers, Dirk Weißenborn, Anastasia Krithara, Sergios Petridis, Dimitris Polychronopoulos, Yannis Almirantis, John Pavlopoulos, Nicolas Baskiotis, Patrick Gallinari, Thierry Artieres, Axel-Cyril… [find](https://scholar.google.com/scholar?q=George+Tsatsaronis%2C+Georgios+Balikas%2C+Prodromos+Malakasiotis%2C+Ioannis+Partalas%2C+Matthias+Zschunke%2C+Michael+Alvers%2C+Dirk+Wei%C3%9Fenborn%2C+Anastasia+Krithara%2C+Sergios+Petridis%2C+Dimitris+Polychronopoulos%2C+Yan)
54. Haotao Wang, Ziyu Jiang, Yuning You, Yan Han, Gaowen Liu, Jayanth Srinivasa, Ramana Rao Kompella, and Zhangyang Wang. 2023a. Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling. Preprint, arXiv:2304.02806. — [arXiv:2304.02806](https://arxiv.org/abs/2304.02806) [find](https://scholar.google.com/scholar?q=Haotao+Wang%2C+Ziyu+Jiang%2C+Yuning+You%2C+Yan+Han%2C+Gaowen+Liu%2C+Jayanth+Srinivasa%2C+Ramana+Rao+Kompella%2C+and+Zhangyang+Wang%2E+2023a%2E+Graph+mixture+of+experts%3A+Learning+on+large%2Dscale+graphs+with+explicit+dive)
55. Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023b. [Self-knowledge guided retrieval augmentation for large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-self-knowledge-guided-retrieval-augmentation/). Preprint, arXiv:2310.05002.
56. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837. Curran Associates, Inc.

*Updated 31 October 2026*