---
title: "DeepRAG — paper by Guan et al. (2025) — summary and ideas"
description: "Retrieval-augmented LLMs often split complex questions into poor sub-questions… 26.4% accuracy. 42 references, cited by 37 papers here."
authors: ["Xinyan Guan", "Jiali Zeng", "Fandong Meng", "Chunlei Xin", "Yaojie Lu", "Hongyu Lin", "Xianpei Han", "Le Sun", "Jie Zhou"]
year: 2025
venue: "arXiv:2502.01142"
source: "https://arxiv.org/abs/2502.01142"
doi: "10.48550/arxiv.2502.01142"
arxiv: "2502.01142"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/guan-2025-deeprag-thinking-retrieve-step-step/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/guan-2025-deeprag-thinking-retrieve-step-step/)

[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/3/) / DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

# DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

**Authors:** [Xinyan Guan](https://md.research.elamur.ai/free/en/authors/xinyan-guan/), [Jiali Zeng](https://md.research.elamur.ai/free/en/authors/jiali-zeng/), [Fandong Meng](https://md.research.elamur.ai/free/en/authors/fandong-meng/), Chunlei Xin, [Yaojie Lu](https://md.research.elamur.ai/free/en/authors/yaojie-lu/), [Hongyu Lin](https://md.research.elamur.ai/free/en/authors/hongyu-lin/), [Xianpei Han](https://md.research.elamur.ai/free/en/authors/xianpei-han/), [Le Sun](https://md.research.elamur.ai/free/en/authors/le-sun/) and [Jie Zhou](https://md.research.elamur.ai/free/en/authors/jie-zhou/) · **Year:** 2025 · **Venue:** arXiv:2502.01142 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2502.01142) · [PDF](https://arxiv.org/pdf/2502.01142) · [DOI 10.48550/arxiv.2502.01142](https://doi.org/10.48550/arxiv.2502.01142) · [arXiv 2502.01142](https://arxiv.org/abs/2502.01142) · [OpenAlex](https://openalex.org/W4407131376)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [37](https://md.research.elamur.ai/free/en/papers/guan-2025-deeprag-thinking-retrieve-step-step/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Retrieval-augmented LLMs often split complex questions into poor sub-questions and retrieve documents when they don't need to. This wastes resources and can add noise that lowers answer quality. DeepRAG treats retrieval-augmented reasoning as a Markov Decision Process. The model breaks a question into a sequence of subqueries (the "retrieval narrative"). For each one, it makes an "atomic decision": search external sources or answer from its own parametric knowledge. Training has two stages, both built on Binary Tree Search. That search explores both options for every subquery.

1. **Imitation Learning:** the model is trained on the correct reasoning path that uses the fewest retrievals.
2. **Chain of Calibration:** preference pairs refine each atomic decision, so the model better recognizes the limits of its own knowledge.

Across in-distribution, out-of-distribution, time-sensitive and heterogeneous-knowledge-base QA settings, DeepRAG answers more accurately while retrieving less. This matters because any LLM can be trained end-to-end to decide when and what to search, without extra classifier heads or uncertainty thresholds.

## Key points
- The reward counts only correct final answers and assigns a cost to each retrieval, so the model learns to minimize lookups without sacrificing correctness.
- The paper reports a 26.4% accuracy improvement in the abstract and conclusion, but a 21.99% gain in the introduction. Retrieval efficiency improves in both cases.
- Comparisons of inference strategies show:
  - Parametric-only answering scores poorly.
  - Retrieving on every subquery is more accurate but costly, and it is still outperformed by DeepRAG's adaptive choice.
- In ablations, alternative training choices did worse:
  - Imitating the minimum-retrieval path beat imitating the maximum-retrieval or random paths.
  - Sentence-level preference pairs made the model rely too heavily on internal knowledge.
- Most questions were split into 3–5 subqueries but needed only 0–2 retrievals. Code is available at github.com/gxy-gxy/DeepRAG.

*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 · 174 works · 21,355 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 256 works · 25,136 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 196 works · 8,907 citations
- [Institute of Software](https://md.research.elamur.ai/free/en/labs/institute-of-software/) — Research institute, Beijing, China · 30 works · 5,038 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,621 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,888 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works

## Cite

Cite as: Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun and Jie Zhou. 2025. DeepRAG: Thinking to Retrieve Step by Step for Large Language Models. arXiv:2502.01142.

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

```bibtex
@misc{guan2025deeprag,
  title = {{DeepRAG: Thinking to Retrieve Step by Step for Large Language Models}},
  author = {Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun and Jie Zhou},
  year = {2025},
  doi = {10.48550/arxiv.2502.01142},
  eprint = {2502.01142},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2502.01142}
}
```

- [← previous AI-Researcher: Autonomous Scientific Innovation](https://md.research.elamur.ai/free/en/papers/tang-2025-ai-researcher-autonomous-scientific/)
- [next → FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://md.research.elamur.ai/free/en/papers/weller-2025-followir-evaluating-teaching-information-retrieval/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

42 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Xinyan Guan, Yanjiang Liu, Xinyu Lu, Boxi Cao, Ben He, Xianpei Han, Le Sun, Jie Lou, Bowen Yu, Yaojie Lu, et al. 2024b. [Search, verify and feedback: Towards next generation post-training paradigm of foundation models via verifier engineering](https://md.research.elamur.ai/free/en/papers/guan-2024-search-verify-feedback-towards-next/). arXiv preprint arXiv:2411.11504.
2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). arXiv preprint arXiv:2310.11511.
3. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. [Semantic parsing on freebase from question-answer pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In Proceedings of the 2013 conference on empirical methods in natural language processing, pages 1533–1544.
4. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
5. Hung-Ting Chen, Fangyuan Xu, Shane Arora, and Eunsol Choi. 2023. [Understanding retrieval augmentation for long-form question answering](https://md.research.elamur.ai/free/en/papers/chen-2023-understanding-retrieval-augmentation-long-form/). arXiv preprint arXiv:2310.12150.
6. 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/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Comm…
7. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025. [Towards reasoning era: A survey of long chain-of-thought for reasoning large language models](https://md.research.elamur.ai/free/en/papers/chen-2025-towards-reasoning-era-survey-long/). arXiv preprint arXiv:2503.09567.
8. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2023. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems.
9. Qinyuan Cheng, Xiaonan Li, Shimin Li, Qin Zhu, Zhangyue Yin, Yunfan Shao, Linyang Li, Tianxiang Sun, Hang Yan, and Xipeng Qiu. 2024. Unified active retrieval for retrieval augmented generation. arXiv preprint arXiv:2406.12534. [find](https://scholar.google.com/scholar?q=Qinyuan+Cheng%2C+Xiaonan+Li%2C+Shimin+Li%2C+Qin+Zhu%2C+Zhangyue+Yin%2C+Yunfan+Shao%2C+Linyang+Li%2C+Tianxiang+Sun%2C+Hang+Yan%2C+and+Xipeng+Qiu%2E+2024%2E+Unified+active+retrieval+for+retrieval+augmented+generation%2E+arXiv+)
10. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2024. [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://md.research.elamur.ai/free/en/papers/jeong-2024-adaptive-rag-learning-adapt-retrieval/). arXiv preprint arXiv:2403.14403. on Natural Language Processing (EMNLP-IJCNLP), pages 2463–2473, Hong Kong, China. Ass…
11. Aske Plaat, Annie Wong, Suzan Verberne, Joost Broekens, Niki van Stein, and Thomas Back. 2024. [Reasoning with large language models, a survey](https://md.research.elamur.ai/free/en/papers/plaat-2024-multi-step-reasoning-large-language/). arXiv preprint arXiv:2407.11511.
12. 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/).
13. Ansh Radhakrishnan, Karina Nguyen, Anna Chen, Carol Chen, Carson Denison, Danny Hernandez, Esin Durmus, Evan Hubinger, Jackson Kernion, Kamilė Lukošiūtė, et al. 2023. Question decomposition improves the faithfulness of model-generated reasoning. arXiv preprint arXiv:2307.11768. [find](https://scholar.google.com/scholar?q=Ansh+Radhakrishnan%2C+Karina+Nguyen%2C+Anna+Chen%2C+Carol+Chen%2C+Carson+Denison%2C+Danny+Hernandez%2C+Esin+Durmus%2C+Evan+Hubinger%2C+Jackson+Kernion%2C+Kamile%CC%87+Luko%C5%A1iu%CC%84te%CC%87%2C+et+al%2E+2023%2E+Question+decomposition+improve)
14. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). arXiv preprint arXiv:2503.09516.
15. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
16. Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, and Andrew Gordon Wilson. 2024a. Large language models must be taught to know what they don’t know. arXiv preprint arXiv:2406.08391. [find](https://scholar.google.com/scholar?q=Sanyam+Kapoor%2C+Nate+Gruver%2C+Manley+Roberts%2C+Katherine+Collins%2C+Arka+Pal%2C+Umang+Bhatt%2C+Adrian+Weller%2C+Samuel+Dooley%2C+Micah+Goldblum%2C+and+Andrew+Gordon+Wilson%2E+2024a%2E+Large+language+models+must+be+taugh)
17. Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. [R1-searcher: Incentivizing the search capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/song-2025-r1-searcher-incentivizing-search/). arXiv preprint arXiv:2503.05592.
18. Sanyam Kapoor, Nate Gruver, Manley Roberts, Arka Pal, Samuel Dooley, Micah Goldblum, and Andrew Wilson. 2024b. Calibration-tuning: Teaching large language models to know what they don‘t know. In Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), pages 1–14, St Julians, Malt… [find](https://scholar.google.com/scholar?q=Sanyam+Kapoor%2C+Nate+Gruver%2C+Manley+Roberts%2C+Arka+Pal%2C+Samuel+Dooley%2C+Micah+Goldblum%2C+and+Andrew+Wilson%2E+2024b%2E+Calibration%2Dtuning%3A+Teaching+large+language+models+to+know+what+they+don%E2%80%98t+know%2E+In+Proce)
19. Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, and Yiqun Liu. 2024. [DRAGIN: Dynamic retrieval augmented generation based on the real-time information needs of large language models](https://md.research.elamur.ai/free/en/papers/su-2024-dragin-dynamic-retrieval-augmented-generation/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
20. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). arXiv preprint arXiv:2501.05366.
21. Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction, 2nd edition. The MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Richard+S%2E+Sutton+and+Andrew+G%2E+Barto%2E+2018%2E+Reinforcement+Learning%3A+An+Introduction%2C+2nd+edition%2E+The+MIT+Press%2C+Cambridge%2C+MA%2E)
22. Yanjiang Liu, Shuhen Zhou, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. 2025. Auto-rt: Automatic jailbreak strategy exploration for red-teaming large language models. arXiv preprint arXiv:2501.01830. — [arXiv:2501.01830](https://arxiv.org/abs/2501.01830) [find](https://scholar.google.com/scholar?q=Yanjiang+Liu%2C+Shuhen+Zhou%2C+Yaojie+Lu%2C+Huijia+Zhu%2C+Weiqiang+Wang%2C+Hongyu+Lin%2C+Ben+He%2C+Xianpei+Han%2C+and+Le+Sun%2E+2025%2E+Auto%2Drt%3A+Automatic+jailbreak+strategy+exploration+for+red%2Dteaming+large+language+mod)
23. Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, and Xueqi Cheng. 2024. Blinded by generated contexts: How language models merge generated and retrieved contexts for open-domain qa? arXiv preprint arXiv:2401.11911. — [arXiv:2401.11911](https://arxiv.org/abs/2401.11911) [find](https://scholar.google.com/scholar?q=Hexiang+Tan%2C+Fei+Sun%2C+Wanli+Yang%2C+Yuanzhuo+Wang%2C+Qi+Cao%2C+and+Xueqi+Cheng%2E+2024%2E+Blinded+by+generated+contexts%3A+How+language+models+merge+generated+and+retrieved+contexts+for+open%2Ddomain+qa%3F+arXiv+prep)
24. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint arXiv:2212.10511. [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2022%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem)
25. Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwq%3A+Reflect+deeply+on+the+boundaries+of+the+unknown%2E)
26. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational 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+musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Transactions+of+the+Association+for+Computational+Li)
27. OpenAI. Hello gpt-4o. [https://openai.com/index/](https://openai.com/index/) hello-gpt-4o/. [Online; accessed 22-January-2025]. [↗](https://openai.com/index/)
28. Ruotong Pan, Boxi Cao, Hongyu Lin, Xianpei Han, Jia Zheng, Sirui Wang, Xunliang Cai, and Le Sun. 2024. Not all contexts are equal: Teaching llms credibility-aware generation. arXiv preprint arXiv:2404.06809. [find](https://scholar.google.com/scholar?q=Ruotong+Pan%2C+Boxi+Cao%2C+Hongyu+Lin%2C+Xianpei+Han%2C+Jia+Zheng%2C+Sirui+Wang%2C+Xunliang+Cai%2C+and+Le+Sun%2E+2024%2E+Not+all+contexts+are+equal%3A+Teaching+llms+credibility%2Daware+generation%2E+arXiv+preprint+arXiv%3A2404)
29. Liang Wang, Haonan Chen, Nan Yang, Xiaolong Huang, Zhicheng Dou, and Furu Wei. 2025. Chain-of-retrieval augmented generation. arXiv preprint arXiv:2501.14342. — [arXiv:2501.14342](https://arxiv.org/abs/2501.14342) [find](https://scholar.google.com/scholar?q=Liang+Wang%2C+Haonan+Chen%2C+Nan+Yang%2C+Xiaolong+Huang%2C+Zhicheng+Dou%2C+and+Furu+Wei%2E+2025%2E+Chain%2Dof%2Dretrieval+augmented+generation%2E+arXiv+preprint+arXiv%3A2501%2E14342%2E+%E2%80%94+%5BarXiv%3A2501%2E14342%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
30. Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander Miller. 2019. [Language models as knowledge bases?](https://md.research.elamur.ai/free/en/papers/petroni-2019-language-models-as-knowledge-bases/) In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference Jason Wei,…
31. Xueru Wen, Xinyu Lu, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. 2024. On-policy fine-grained knowledge feedback for hallucination mitigation. arXiv preprint arXiv:2406.12221. — [arXiv:2406.12221](https://arxiv.org/abs/2406.12221) [find](https://scholar.google.com/scholar?q=Xueru+Wen%2C+Xinyu+Lu%2C+Xinyan+Guan%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Xianpei+Han%2C+and+Le+Sun%2E+2024%2E+On%2Dpolicy+fine%2Dgrained+knowledge+feedback+for+hallucination+mitigation%2E+arXiv+preprint+arXiv%3A2406%2E12221%2E)
32. Zihan Zhang, Meng Fang, and Ling Chen. 2024. Retrievalqa: Assessing adaptive retrieval-augmented generation for short-form open-domain question answering. arXiv preprint arXiv:2402.16457. [find](https://scholar.google.com/scholar?q=Zihan+Zhang%2C+Meng+Fang%2C+and+Ling+Chen%2E+2024%2E+Retrievalqa%3A+Assessing+adaptive+retrieval%2Daugmented+generation+for+short%2Dform+open%2Ddomain+question+answering%2E+arXiv+preprint+arXiv%3A2402%2E16457%2E)
33. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, and Bin Cui. 2024. [Retrieval-augmented generation for ai-generated content: A survey](https://md.research.elamur.ai/free/en/papers/zhao-2024-retrieval-augmented-generation-ai-generated/). arXiv preprint arXiv:2402.19473.
34. Zhuofeng Wu, He Bai, Aonan Zhang, Jiatao Gu, VG Vydiswaran, Navdeep Jaitly, and Yizhe Zhang. 2024. Divide-or-conquer? which part should you distill your llm? arXiv preprint arXiv:2402.15000. [find](https://scholar.google.com/scholar?q=Zhuofeng+Wu%2C+He+Bai%2C+Aonan+Zhang%2C+Jiatao+Gu%2C+VG+Vydiswaran%2C+Navdeep+Jaitly%2C+and+Yizhe+Zhang%2E+2024%2E+Divide%2Dor%2Dconquer%3F+which+part+should+you+distill+your+llm%3F+arXiv+preprint+arXiv%3A2402%2E15000%2E)
35. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai D… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
36. 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.
37. Xunjian Yin, Xu Zhang, Jie Ruan, and Xiaojun Wan. 2024. Benchmarking knowledge boundary for large language model: A different perspective on model evaluation. arXiv preprint arXiv:2402.11493. — [arXiv:2402.11493](https://arxiv.org/abs/2402.11493) [find](https://scholar.google.com/scholar?q=Xunjian+Yin%2C+Xu+Zhang%2C+Jie+Ruan%2C+and+Xiaojun+Wan%2E+2024%2E+Benchmarking+knowledge+boundary+for+large+language+model%3A+A+different+perspective+on+model+evaluation%2E+arXiv+preprint+arXiv%3A2402%2E11493%2E+%E2%80%94+%5BarXiv)
38. Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Xuanjing Huang. 2023. Do large language models know what they don’t know? arXiv preprint arXiv:2305.18153. [find](https://scholar.google.com/scholar?q=Zhangyue+Yin%2C+Qiushi+Sun%2C+Qipeng+Guo%2C+Jiawen+Wu%2C+Xipeng+Qiu%2C+and+Xuanjing+Huang%2E+2023%2E+Do+large+language+models+know+what+they+don%E2%80%99t+know%3F+arXiv+preprint+arXiv%3A2305%2E18153%2E)
39. Tian Yu, Shaolei Zhang, and Yang Feng. 2024. Auto-rag: Autonomous retrieval-augmented generation for large language models. [find](https://scholar.google.com/scholar?q=Tian+Yu%2C+Shaolei+Zhang%2C+and+Yang+Feng%2E+2024%2E+Auto%2Drag%3A+Autonomous+retrieval%2Daugmented+generation+for+large+language+models%2E)
40. Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2022. [Generate rather than retrieve: Large language models are strong context generators](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/). arXiv preprint arXiv:2209.10063.
41. Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, and Michael Bendersky. 2024. Inference scaling for long-context retrieval augmented generation. arXiv preprint arXiv:2410.04343. — [arXiv:2410.04343](https://arxiv.org/abs/2410.04343) [find](https://scholar.google.com/scholar?q=Zhenrui+Yue%2C+Honglei+Zhuang%2C+Aijun+Bai%2C+Kai+Hui%2C+Rolf+Jagerman%2C+Hansi+Zeng%2C+Zhen+Qin%2C+Dong+Wang%2C+Xuanhui+Wang%2C+and+Michael+Bendersky%2E+2024%2E+Inference+scaling+for+long%2Dcontext+retrieval+augmented+gener)
42. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, and Shuming Shi. 2023. [Siren’s song in the ai ocean: A survey on hallucination in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/). arXiv preprint arXiv:2309.01219.

*Updated 3 November 2026*