CoChat
Sign Up
Cited by 35Topic ModelingInformation Retrieval and Search BehaviorNatural Language Processing Techniques

The DOI matches its Crossref record.

M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions

Open access
Wang, Zheng, Teo, Shu, Ouyang, Jieer, Xu, Yongjun, Shi, Wei·2024·Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
DOI 10.18653/v1/2024.acl-long.108
Open this paper in CoChat — free accountOpen PDF

Abstract

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database.However, existing RAG methods typically organize all memories in a whole database, potentially limiting focus on crucial memories and introducing noise.In this paper, we introduce a multiple partition paradigm for RAG (called M-RAG), where each database partition serves as a basic unit for RAG execution.Based on this paradigm, we propose a novel framework that leverages LLMs with Multi-Agent Reinforcement Learning to optimize different language generation tasks explicitly.Through comprehensive experiments conducted on seven datasets, spanning three language generation tasks and involving three distinct language model architectures, we confirm that M-RAG consistently outperforms various baseline methods, achieving improvements of 11%, 8%, and 12% for text summarization, machine translation, and dialogue generation, respectively.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2024.acl-long.108

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 58

  1. Nathan Anderson, Caleb Wilson, and Stephen D. Richardson. 2022. Lingua: Addressing scenarios for live interpretation and automatic dubbing. In AMTA, pages 202-209.
  2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. CoRR, abs/2310.11511. · arXiv
  3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. NeurIPS, 33:1877-1901.
  4. Howard Chen, Ramakanth Pasunuru, Jason Weston, and Asli Celikyilmaz. 2023. Walking down the mem- ory maze: Beyond context limit through interactive reading. CoRR, abs/2310.05029. · arXiv
  5. Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, and Qi Zhang. 2023a. UPRISE: universal prompt retrieval for improving zero-shot evaluation. In EMNLP, pages 12318-12337.
  6. Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, and Rui Yan. 2023b. Lift yourself up: Retrieval-augmented text generation with self memory. NeurIPS.
  7. Woon Sang Cho, Pengchuan Zhang, Yizhe Zhang, Xiu- jun Li, Michel Galley, Chris Brockett, Mengdi Wang, and Jianfeng Gao. 2018. Towards coherent and cohe- sive long-form text generation. CoRR.
  8. Zhuyun Dai, Vincent Y. Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith B. Hall, and Ming-Wei Chang. 2023. Promptagator: Few-shot dense retrieval from 8 examples. In ICLR.
  9. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval- augmented generation for large language models: A survey. CoRR, abs/2312.10997. · arXiv
  10. Siddharth Gollapudi, Neel Karia, Varun Sivashankar, Ravishankar Krishnaswamy, Nikit Begwani, Swapnil Raz, Yiyong Lin, Yin Zhang, Neelam Mahapatro, Premkumar Srinivasan, et al. 2023. Filtered-diskann: Graph algorithms for approximate nearest neighbor search with filters. In WWW, pages 3406-3416.
  11. Jiatao Gu, Yong Wang, Kyunghyun Cho, and Victor O. K. Li. 2018. Search engine guided neural machine translation. In AAAI, pages 5133-5140. AAAI Press.
  12. Rentong Guo, Xiaofan Luan, Long Xiang, Xiao Yan, Xiaomeng Yi, Jigao Luo, Qianya Cheng, Weizhi Xu, Jiarui Luo, Frank Liu, et al. 2022. Manu: a cloud native vector database management system. PVLDB, 15(12):3548-3561.
  13. Yikun Han, Chunjiang Liu, and Pengfei Wang. 2023. A comprehensive survey on vector database: Storage and retrieval technique, challenge. CoRR.
  14. Nabil Hossain, Marjan Ghazvininejad, and Luke Zettle- moyer. 2020. Simple and effective retrieve-edit- rerank text generation. In ACL, pages 2532-2538.
  15. Piotr Indyk and Rajeev Motwani. 1998. Approximate nearest neighbors: towards removing the curse of dimensionality. In STOC, pages 604-613.
  16. Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard. 2019. Way off- policy batch deep reinforcement learning of implicit human preferences in dialog. CoRR.
  17. Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. TPAMI, 33(1):117-128.
  18. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Men- sch, Chris Bamford, and et al. 2023a. Mistral 7b. CoRR, abs/2310.06825. · arXiv
  19. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, and Arthur Mensch et al. 2024. Mixtral of experts. CoRR, abs/2401.04088. · arXiv
  20. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023b. Llmlingua: Compressing prompts for accelerated inference of large language models. In EMNLP, pages 13358-13376.
  21. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick S. H. Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. In EMNLP (1), pages 6769-6781.
  22. Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, and Stefan Riezler. 2018. Can neural machine translation be improved with user feedback? CoRR.
  23. Carolin Lawrence and Stefan Riezler. 2018. Improving a neural semantic parser by counterfactual learning from human bandit feedback. CoRR.
  24. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Hein- rich Küttler, Mike Lewis, Wen-tau Yih, Tim Rock- täschel, et al. 2020. Retrieval-augmented genera- tion for knowledge-intensive nlp tasks. NeurIPS, 33:9459-9474.
  25. Jinpeng Li, Yingce Xia, Rui Yan, Hongda Sun, Dongyan Zhao, and Tie-Yan Liu. 2021. Stylized dialogue gen- eration with multi-pass dual learning. In NeurIPS, pages 28470-28481.
  26. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting ob- jective function for neural conversation models. In HLT-NAACL, pages 110-119.
  27. Xinze Li, Zhenghao Liu, Chenyan Xiong, Shi Yu, Yu Gu, Zhiyuan Liu, and Ge Yu. 2023. Structure- aware language model pretraining improves dense retrieval on structured data. In ACL (Findings), pages 11560-11574.
  28. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. Dailydialog: A manually labelled multi-turn dialogue dataset. In IJCNLP(1), pages 986-995.
  29. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74-81.
  30. Xi Victoria Lin, Xilun Chen, Mingda Chen, Wei- jia Shi, Maria Lomeli, Rich James, Pedro Ro- driguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, and Scott Yih. 2023. RA-DIT: retrieval-augmented dual instruction tuning. CoRR, abs/2310.01352. · arXiv
  31. Ron Litman, Oron Anschel, Shahar Tsiper, Roee Lit- man, Shai Mazor, and R. Manmatha. 2020. SCAT- TER: selective context attentional scene text recog- nizer. In CVPR, pages 11959-11969.
  32. Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting for retrieval- augmented large language models. EMNLP, pages 5303-5315.
  33. Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. TPAMI, 42(4):824-836.
  34. Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, and et al. 2024. Gemma: Open models based on gemini research and technology. CoRR, abs/2403.08295. · arXiv
  35. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. CoRR.
  36. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, and Jeff Wu et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. CoRR, abs/2112.09332. · arXiv
  37. Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. Don't give me the details, just the summary! topic-aware convolutional neural networks for ex- treme summarization. In EMNLP, pages 1797-1807.
  38. Arvind Neelakantan, Tao Xu, Raul Puri, Alec Rad- ford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022. Text and code embeddings by contrastive pre- training. CoRR.
  39. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instruc- tions with human feedback. NeurIPS, 35:27730- 27744.
  40. James Jie Pan, Jianguo Wang, and Guoliang Li. 2023. Survey of vector database management systems. CoRR.
  41. Matt Post. 2018. A call for clarity in reporting BLEU scores. In WMT, pages 186-191.
  42. Eva Sharma, Chen Li, and Lu Wang. 2019. BIG- PATENT: A large-scale dataset for abstractive and coherent summarization. In ACL (1), pages 2204- 2213.
  43. Aleksandrs Slivkins et al. 2019. Introduction to multi- armed bandits. Foundations and Trends® in Machine Learning, 12(1-2):1-286.
  44. Ralf Steinberger, Bruno Pouliquen, Anna Widiger, Camelia Ignat, Tomaz Erjavec, Dan Tufis, and Dániel Varga. 2006. The jrc-acquis: A multilingual aligned parallel corpus with 20+ languages. In LREC, pages 2142-2147.
  45. Hugo Touvron, Louis Martin, Kevin Stone, and Peter Al- bert et al. 2023. Llama 2: Open foundation and fine-tuned chat models. CoRR, abs/2307.09288. · arXiv
  46. Shuohang Wang, Yichong Xu, Yuwei Fang, Yang Liu, Siqi Sun, Ruochen Xu, Chenguang Zhu, and Michael Zeng. 2022. Training data is more valuable than you think: A simple and effective method by retrieving from training data. In ACL, pages 3170-3179.
  47. Xintao Wang, Qianwen Yang, Yongting Qiu, Jiaqing Liang, Qianyu He, Zhouhong Gu, Yanghua Xiao, and Wei Wang. 2023a. Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. CoRR, abs/2308.11761. · arXiv
  48. Zheng Wang, Bingzheng Gan, and Wei Shi. 2024. Mul- timodal query suggestion with multi-agent reinforce- ment learning from human feedback. In WWW, pages 1374-1385.
  49. Zheng Wang, Cheng Long, Gao Cong, and Christian S. Jensen. 2023b. Collectively simplifying trajectories in a database: A query accuracy driven approach. CoRR, abs/2311.11204. · arXiv
  50. Zheng Wang, Cheng Long, Gao Cong, and Qianru Zhang. 2021. Error-bounded online trajectory sim- plification with multi-agent reinforcement learning. In KDD, pages 1758-1768.
  51. Jeff Wu, Long Ouyang, Daniel M Ziegler, Nisan Sti- ennon, Ryan Lowe, Jan Leike, and Paul Christiano. 2021a. Recursively summarizing books with human feedback. CoRR.
  52. Sixing Wu, Ying Li, Minghui Wang, Dawei Zhang, Yang Zhou, and Zhonghai Wu. 2021b. More is bet- ter: Enhancing open-domain dialogue generation via multi-source heterogeneous knowledge. In EMNLP, pages 2286-2300.
  53. Sixing Wu, Ying Li, Dawei Zhang, and Zhonghai Wu. 2022. KSAM: infusing multi-source knowledge into dialogue generation via knowledge source aware multi-head decoding. In ACL (Findings), pages 353- 363.
  54. Shitao Xiao, Zheng Liu, Peitian Zhang, and Xin- grun Xing. 2023. Lm-cocktail: Resilient tuning of language models via model merging. CoRR, abs/2311.13534. · arXiv
  55. Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2023. RECOMP: improving retrieval-augmented lms with compression and selective augmentation. CoRR, abs/2310.04408. · arXiv
  56. Wenzhuo Xue, Hui Li, Yanguo Peng, Jiangtao Cui, and Yu Shi. 2017. Secure k nearest neighbors query for high-dimensional vectors in outsourced environ- ments. IEEE TBD, 4(4):586-599.
  57. Sanghyun Yi, Rahul Goel, Chandra Khatri, Alessan- dra Cervone, Tagyoung Chung, Behnam Hedayatnia, Anu Venkatesh, Raefer Gabriel, and Dilek Hakkani- Tur. 2019. Towards coherent and engaging spoken dialog response generation using automatic conversa- tion evaluators. CoRR.
  58. Shengyao Zhuang, Bing Liu, Bevan Koopman, and Guido Zuccon. 2023. Open-source large language models are strong zero-shot query likelihood models for document ranking. In EMNLP (Findings), pages 8807-8817.

Cited by

See all 35

Metadata

Authors
Wang, Z., Teo, S., Ouyang, J., Xu, Y., & Shi, W.
Affiliations
Huawei Technologies (China) (CN)
ORCID
Venue
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Publisher
Association for Computational Linguistics
Published
2024
Pages
1966-1978
ISSN
0736-587X (ISSN-L)
DOI
10.18653/v1/2024.acl-long.108
OpenAlex
W4402671970
Cited by
35
References
0
Citations by year
2026: 11 · 2025: 22 · 2024: 2
FWCI
8.46
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, public-domain)
  • arXiv (Cornell University) (public-domain)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
retrieval-augmented generation, large language models, database partitioning, multi-agent reinforcement learning, memory retrieval, text summarization, machine translation, dialogue generation, language generation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions. https://app.cochat.ai/papers/10.18653/v1/2024.acl-long.108
The paper
Wang, Z., Teo, S., Ouyang, J., Xu, Y., & Shi, W. (2024). M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2024.acl-long.108