EMNLP Findings2025
DeepNote: Note-Centric Deep Retrieval-Augmented Generation
Ruobing Wang, Qingfei Zhao, Yukun Yan, Daren Zha, Yuxuan Chen, Shi Yu, Zhenghao Liu, Yixuan Wang, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
Abstract
Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for questionanswering (QA) by incorporating external knowledge. However, existing adaptive RAG methods rely on LLMs to predict retrieval timing and directly use retrieved information for generation, often failing to reflect real information needs and fully leverage retrieved knowledge. We develop DeepNote, an adaptive RAG framework that achieves in-depth and robust exploration of knowledge sources through note-centric adaptive retrieval. Deep-Note employs notes as carriers for refining and accumulating knowledge. During in-depth exploration, it uses these notes to determine retrieval timing, formulate retrieval queries, and iteratively assess knowledge growth, ultimately leveraging the best note for answer generation. Extensive experiments and analyses demonstrate that DeepNote significantly outperforms all baselines and exhibits the ability to gather knowledge with both high density and quality. Additionally, DPO further improves the performance of DeepNote. The code and data are available at https://github.com/ thunlp/DeepNote.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
- HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational ModelingChulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng et al.ICML 2026 · 4 citations
- Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language ModelsHao Chen, Ye He, Yuchun Fan, Yukun Yan et al.ICML 2026 · 2 citations
Builds on16
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- Large Language Models Struggle to Learn Long-Tail KnowledgeNikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace et al.ICML 2023 · 623 citations
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang et al.EMNLP 2023 · 549 citations
Related papers
- DeepRAG: Thinking to Retrieve Step by Step for Large Language ModelsXinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin et al.ICLR 2026 · 30 citations
- SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented GenerationZijun Yao, Weijian Qi, Liangming Pan, Shulin Cao et al.ACL 2025
- In-depth Analysis of Graph-based RAG in a Unified FrameworkYingli Zhou, Yaodong Su, Youran Sun, Shu Wang et al.VLDB 2025 · 48 citations
- Fine-grained Knowledge Enhancement for Retrieval-Augmented GenerationJingxuan Han, Zhendong Mao, Yi Liu, Yexuan Che et al.ACL Findings 2025 · 3 citations
- R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement LearningYuan Li, Qi Luo, Xiaonan Li, Bufan Li et al.EMNLP Findings 2025 · 4 citations
