Elamur Research⌕
☰
home / papers / 2025 / DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering

Paper · 2025 · Rong Cheng, Jinyi Liu, Yan Zheng et al.

Summary

Multi-hop question answering requires a model to chain several reasoning steps, and the facts it needs change as the reasoning unfolds. Existing iterative RAG systems retrieve repeatedly, but they often miss when knowledge is lacking, issue poorly targeted queries, and let noisy, fragmented documents accumulate. DualRAG addresses this with two coupled processes. Reasoning-augmented Querying (RaQ) drives the reasoning chain, detects gaps, and uses an Entity Identifier to form entity-specific queries. Progressive Knowledge Aggregation (pKA) reranks and condenses retrieved passages into a per-entity Knowledge Outline, which feeds the next reasoning step. To lower cost, the authors build a dedicated training set and fine-tune smaller models, yielding DualRAG-FT. On several multi-hop QA benchmarks, the framework improves accuracy and coherence over prior methods and comes close to, or occasionally exceeds, a setup with oracle knowledge. The work shows that structuring both what the system asks and what it retains makes retrieval-augmented reasoning more reliable, including on smaller LLMs.

Key points

  • Pipeline components: a Reasoner, an Entity Identifier, a Retriever, a Reranker and a Knowledge Summarizer. At each iteration, RaQ uses the previous Knowledge Outline to produce a reasoning step and queries, and pKA then updates the outline.
  • Ablations (Table 3): each of the following removals lowers performance:
    • disabling the Reasoner's active gap detection (w/o R, which behaves like IRCoT);
    • dropping the Entity Identifier (w/o Ei);
    • replacing the Knowledge Outline with raw retrieval results (w/o KO).
  • DualRAG-FT ablations (Table 4):
    • Fine-tuning all three components (Reasoner, Entity Identifier, Knowledge Summarizer) matters.
    • The fine-tuned Entity Identifier generates fewer redundant queries (Figure 4), which reduces retrieval calls.
  • Other QA tasks: with Qwen2.5-72B-Instruct, DualRAG also outperforms the retrieve-then-read baseline on single-hop QA (e.g., NQ) and on long-form QA (ASQA, ELI5, measured with Rouge-2 and Rouge-L).
  • Limitations and future work: multi-turn retrieval adds latency, and missing, contradictory or outdated corpus content remains a risk. The authors plan to add reinforcement learning and to apply the framework to AI for Science.

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

🎓Tianjin UniversityTianjin · China41 works · 1,128 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksInformation Systems · 1,437 works

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1,426 worksQuestion answering · 441 worksInformation retrieval & search · 473 works

Cite

Cite as Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang and Jianye Hao. 2025. DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering. Proceedings of the 63rd 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. DOI 10.18653/v1/2025.acl-long.1539

@inproceedings{cheng2025dualrag,
  title = {{DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering}},
  author = {Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang and Jianye Hao},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.1539},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1539}
}

References

59 references, 36 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sweta Agrawal, Chunting Zhou, Mike Lewis, Luke Zettlemoyer, and Marjan Ghazvininejad. 2023. In-context examples selection for machine translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics.
  2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations.
  3. Maciej Besta, Ales Kubicek, Roman Niggli, Robert Gerstenberger, Lucas Weitzendorf, Mingyuan Chi, Patrick Iff, Joanna Gajda, Piotr Nyczyk, Jürgen Müller, Hubert Niewiadomski, Marcin Chrapek, Michał Podstawski, and Torsten Hoefler. 2024. Multi-head rag: Solving multi-aspect problems with llms. Preprin… — [arXiv:2406.05085](https://arxiv.org/abs/2406.05085) find
  4. Tianchi Cai, Zhiwen Tan, Xierui Song, Tao Sun, Jiyan Jiang, Yunqi Xu, Yinger Zhang, and Jinjie Gu. 2024. Forag: Factuality-optimized retrieval augmented generation for web-enhanced long-form question answering. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining,… find
  5. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024a. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. Preprint, arXiv:2402.03216.
  6. Jiawei Chen, Hongyu Lin, Xianpei Han, and Le Sun. 2024b. Benchmarking large language models in retrieval-augmented generation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):17754–17762.
  7. Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan Tracey, Francesco Carpanese, Timo Ewalds, Roland Hafner, Abbas Abdolmaleki, Diego de Las Casas, et al. 2022. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature, 602(7897):414–419. find
  8. Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, and Michael Auli. 2019. ELI5: Long form question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3558–3567, Florence, Italy. Association for Computational Linguistics.
  9. 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. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 6491–650…
  10. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2023. Precise zero-shot dense retrieval without relevance labels. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1762–1777, Toronto, Canada. Association for Computational Li…
  11. 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. Preprint, arXiv:2312.10997.
  12. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Comm…
  13. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023a. Llmlingua: Compressing prompts for accelerated inference of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages…
  14. Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2024. LongLLMLingua: Accelerating and enhancing LLMs in long context scenarios via prompt compression. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:…
  15. Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023b. Active retrieval augmented generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992, Singapore. Association f…
  16. Jiajie Jin, Yutao Zhu, Xinyu Yang, Chenghao Zhang, and Zhicheng Dou. 2024. Flashrag: A modular toolkit for efficient retrieval-augmented generation research. Preprint, arXiv:2405.13576. find
  17. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. Preprint, arXiv:2001.08361.
  18. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli…
  19. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural…
  20. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  21. Myeonghwa Lee, Seonho An, and Min-Soo Kim. 2024. PlanRAG: A plan-then-retrieval augmented generation for generative large language models as decision makers. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… find
  22. 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. In Advances in Neural Information Proc…
  23. Yucheng Li. 2023. Unlocking context constraints of llms: Enhancing context efficiency of llms with self-information-based content filtering. Preprint, arXiv:2304.12102.
  24. Zihan Liao, Hang Yu, Jianguo Li, Jun Wang, and Wei Zhang. 2024. D2LLM: Decomposed and distilled large language models for semantic search. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14798–14814, Bangkok, Thailand. Associa… find
  25. Chin-Yew Lin. 2004. Rouge: a package for automatic evaluation of summaries. In Workshop on Text Summarization Branches Out, Post-Conference Workshop of ACL 2004, Barcelona, Spain, pages 74–81.
  26. Jinyi Liu, Yan Zheng, Rong Cheng, Qiyu Wu, Wei Guo, Fei Ni, Hebin Liang, Yifu Yuan, Hangyu Mao, Fuzheng Zhang, and Jianye Hao. 2025. From chaos to order: The atomic reasoner framework for fine-grained reasoning in large language models. Preprint, arXiv:2503.15944. — [arXiv:2503.15944](https://arxiv.org/abs/2503.15944) find
  27. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12:157–173.
  28. Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting in retrieval-augmented large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5303–5315, Singapore. Association for Computational Linguistics.
  29. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… find
  30. Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. 2020. On faithfulness and factuality in abstractive summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1906–1919, Online. Association for Computational Linguistics.
  31. Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou, Jiashun Liu, Yan Zheng, Bin Wang, and Yuzheng Zhuang. 2024a. Generate subgoal images before act: Unlocking the chain-of-thought reasoning in diffusion model for robot manipulation with multimodal prompts. In IEEE/CVF Conference on Computer Vision and Pat… find
  32. Fei Ni, Jianye HAO, Shiguang Wu, Longxin Kou, Yifu Yuan, Zibin Dong, Jinyi Liu, MingZhi Li, Yuzheng Zhuang, and YAN ZHENG. 2024b. PERIA: Perceive, reason, imagine, act via holistic language and vision planning for manipulation. In The Thirty-eighth Annual Conference on Neural Information Processing… find
  33. OpenAI. 2023. GPT-4 technical report. abs/2303.08774.
  34. CoRR, Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11:1316–1331.
  35. Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’20, page 3505–3506,… find
  36. Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389. find
  37. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9248–9274, Singapore. Association for…
  38. Zhengliang Shi, Shuo Zhang, Weiwei Sun, Shen Gao, Pengjie Ren, Zhumin Chen, and Zhaochun Ren. 2024. Generate-then-ground in retrieval-augmented generation for multi-hop question answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  39. Ivan Stelmakh, Yi Luan, Bhuwan Dhingra, and Ming-Wei Chang. 2022. ASQA: Factoid questions meet long-form answers. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8273–8288, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  40. 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. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
  41. Jiejun Tan, Zhicheng Dou, Yutao Zhu, Peidong Guo, Kun Fang, and Ji-Rong Wen. 2024. Small models, big insights: Leveraging slim proxy models to decide when and what to retrieve for LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… find
  42. Qwen Team. 2024. Qwen2.5: A party of foundation models. find
  43. 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
  44. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
  45. Prakhar Verma, Sukruta Prakash Midigeshi, Gaurav Sinha, Arno Solin, Nagarajan Natarajan, and Amit Sharma. 2024. Plan×rag: Planning-guided retrieval augmented generation. Preprint, arXiv:2410.20753. — [arXiv:2410.20753](https://arxiv.org/abs/2410.20753) find
  46. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. CoRR, abs/2212.03533.
  47. Liang Wang, Nan Yang, and Furu Wei. 2023a. Query2doc: Query expansion with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9414–9423, Singapore. Association for Computational Linguistics.
  48. Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023b. Self-knowledge guided retrieval augmentation for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315, Singapore. Association for Computational Linguistics.
  49. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. C-pack: Packaged resources to advance general chinese embedding. Preprint, arXiv:2309.07597.
  50. Yihang Xiao, Jinyi Liu, Yan Zheng, Xiaohan Xie, Jianye Hao, Mingzhi Li, Ruitao Wang, Fei Ni, Yuxiao Li, Jintian Luo, et al. 2024. Cellagent: An llm-driven multi-agent framework for automated single-cell data analysis. arXiv preprint arXiv:2407.09811. diverse, explainable multi-hop question answering… — [arXiv:2407.09811](https://arxiv.org/abs/2407.09811) find
  51. Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2024. Making retrieval-augmented language models robust to irrelevant context. In The Twelfth International Conference on Learning Representations.
  52. Hao Yu, Aoran Gan, Kai Zhang, Shiwei Tong, Qi Liu, and Zhaofeng Liu. 2024a. Evaluation of retrieval-augmented generation: A survey. Preprint, arXiv:2405.07437. — [arXiv:2405.07437](https://arxiv.org/abs/2405.07437) find
  53. Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. 2024b. Rankrag: Unifying context ranking with retrieval-augmented generation in llms. Preprint, arXiv:2407.02485. — [arXiv:2407.02485](https://arxiv.org/abs/2407.02485) find
  54. Yan Zheng, Xiaofei Xie, Ting Su, Lei Ma, Jianye Hao, Zhaopeng Meng, Yang Liu, Ruimin Shen, Yingfeng Chen, and Changjie Fan. 2019. Wuji: Automatic online combat game testing using evolutionary deep reinforcement learning. In 2019 34th IEEE/ACM International Conference on Automated Software Engineerin… find
  55. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, and Zheyan Luo. 2024. LlamaFactory: Unified efficient fine-tuning of 100+ language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 400–410, Bangkok, Thail…
  56. Chunting Zhou, Graham Neubig, Jiatao Gu, Mona Diab, Francisco Guzmán, Luke Zettlemoyer, and Marjan Ghazvininejad. 2021. Detecting hallucinated content in conditional neural sequence generation. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1393–1404, Online. As…
  57. Yujia Zhou, Zheng Liu, Jiajie Jin, Jian-Yun Nie, and Zhicheng Dou. 2024. Metacognitive retrieval-augmented large language models. In Proceedings of the ACM Web Conference 2024, WWW ’24, page 1453–1463, New York, NY, USA. Association for Computing Machinery. find
  58. Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, and Jie Zhou. 2024. Unsupervised information refinement training of large language models for retrieval-augmented generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:… find
  59. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A dataset for find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/cheng-2025-dualrag-dual-process-approach-integrate/