EventRAG: Enhancing LLM Generation with Event Knowledge Graphs
Open accessAbstract
Retrieval-augmented generation (RAG) systems often struggle with narrative-rich documents and event-centric reasoning, particularly when synthesizing information across multiple sources.We present EventRAG, a novel framework that enhances text generation through structured event representations.We first construct an Event Knowledge Graph by extracting events and merging semantically equivalent nodes across documents, while expanding under-connected relationships.We then employ an iterative retrieval and inference strategy that explicitly captures temporal dependencies and logical relationships across events.Experiments on UltraDomain and MultiHo-pRAG benchmarks show EventRAG's superiority over baseline RAG systems, with substantial gains in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.Our work advances RAG systems by integrating structured event semantics with iterative inference, particularly benefiting scenarios requiring temporal and logical reasoning across documents.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
Even when structured memory is introduced, existing methods often struggle to explicitly capture logical relationships among experiences or memory units.
“Even when structured memory is introduced, existing methods often struggle to explicitly capture the logical relationships among experiences or memory units.”
From Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning (2026) · cites this paper as Yang et al., 2025
The Graph-Based Language Models section says earlier structured representations tend to model static relationships rather than dynamic events, supporting the concern that structure alone may not capture event relationships. The paper discusses events in RAG systems, however, not structured memory or relationships among experiences or memory units; that extension is not established by this source. No page number is available in our copy. (LLM, conf=0.83)
Experimental — accuracy not yet measuredBy treating temporally situated events as primary memory units, the resulting event graph preserves narrative structure and event-level semantics, which are often lost in triple-based representations.
“By treating temporally situated events as primary memory units, the resulting event graph preserves narrative structure and event-level semantics, which are often lost in triple-based representations (Yang et al., 2025).”
From Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning (2026) · cites this paper as Yang et al., 2025
Section 2.1 describes EventRAG as event-centric and temporally grounded, capturing relationships and sequences between events in narrative-rich text. The Temporal-Aware Limitations section says conventional RAG can lose coherent timelines, but the cited passages do not establish that triple-based representations often lose narrative structure or event-level semantics. Page numbers are unavailable in our copy. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
LightRAG: Simple and Fast Retrieval-Augmented Generation
Guo, Z., Xia, L., Yu, Y., Ao, T., & Huang, C. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.568 · Cited by 208
Flagged first, then by citations
Research works printed but not linked: 25
- Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Self-reflective retrieval augmented generation. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Fol- lowing.
- William Brannon, Wonjune Kang, Suyash Fulay, Hang Jiang, Brandon Roy, Deb Roy, and Jad Kabbara. 2023. Congrat: Self-supervised contrastive pretraining for joint graph and text embeddings. arXiv preprint arXiv:2305.14321. · arXiv
- Michael Bugert, Nils Reimers, and Iryna Gurevych. 2021. Generalizing cross-document event corefer- ence resolution across multiple corpora. Computa- tional Linguistics, 47(3):575-614.
- Huajun Chen. 2024. Large knowledge model: Perspec- tives and challenges. Data Intelligence, 6(3):587- 620.
- Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. · arXiv
- Shahul Es, Jithin James, Luis Espinosa Anke, and Steven Schockaert. 2024. Ragas: Automated evaluation of retrieval augmented generation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 150-158.
- 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 Pro- ceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6491- 6501.
- Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, and Jie Zhou. 2025. Deeprag: Thinking to retrieval step by step for large language models. arXiv preprint arXiv:2502.01142. · arXiv
- 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. arXiv preprint arXiv:2501.05366. · arXiv
- Yichuan Li, Kaize Ding, and Kyumin Lee. 2023. Grenade: Graph-centric language model for self- supervised representation learning on text-attributed graphs. In Findings of the Association for Computa- tional Linguistics: EMNLP 2023, pages 2745-2757.
- Hao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen, and Muhan Zhang. 2023. One for all: Towards training one graph model for all classification tasks. arXiv preprint arXiv:2310.00149. · arXiv
- Qingwen Liu, Zejun Li, Zhihao Fan, Cunxiang Yin, Yancheng He, Jing Cai, Jinhua Fu, and Zhongyu Wei. 2025. Bridging the domain gap in grounded situation recognition via unifying event extraction across modalities. Data Intelligence, 7(1):143-162.
- Yujie Luo, Xiangyuan Ru, Kangwei Liu, Lin Yuan, Mengshu Sun, Ningyu Zhang, Lei Liang, Zhiqiang Zhang, Jun Zhou, Lanning Wei, et al. 2024. Oneke: A dockerized schema-guided llm agent- based knowledge extraction system. arXiv preprint arXiv:2412.20005. · arXiv
- Odhran ODonoghue, Aleksandar Shtedritski, John Ginger, Ralph Abboud, Ali Essam Ghareeb, and Samuel G Rodriques. Bioplanner: Automatic evalua- tion of llms on protocol planning in biology. In The 2023 Conference on Empirical Methods in Natural Language Processing.
- Hongjin Qian, Peitian Zhang, Zheng Liu, Kelong Mao, and Zhicheng Dou. 2024. Memorag: Moving to- wards next-gen rag via memory-inspired knowledge discovery. arXiv preprint arXiv:2409.05591. · arXiv
- Rahul Ravi, Gouri Ginde, and Jon Rokne. 2024. Pragyan- connecting the dots in tweets. In International Con- ference on Advances in Social Networks Analysis and Mining, pages 338-354. Springer.
- Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. 2024. Graphgpt: Graph instruction tuning for large language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Develop- ment in Information Retrieval, pages 491-500.
- Yixuan Tang and Yi Yang. 2024. Multihop-rag: Bench- marking retrieval-augmented generation for multi-hop queries. arXiv preprint arXiv:2401.15391. · arXiv
- Haoyu Wang, Hongming Zhang, Yuqian Deng, Jacob Gardner, Dan Roth, and Muhao Chen. 2023. Ex- tracting or guessing? improving faithfulness of event temporal relation extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 541-553.
- Xiang Wei, Yufeng Chen, Ning Cheng, Xingyu Cui, Jinan Xu, and Wenjuan Han. 2024. Collabkg: A learnable human-machine-cooperative information extraction toolkit for (event) knowledge graph con- struction. In Proceedings of the 2024 Joint Inter- national Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3490-3506.
- Han Xie, Da Zheng, Jun Ma, Houyu Zhang, Vassilis N Ioannidis, Xiang Song, Qing Ping, Sheng Wang, Carl Yang, Yi Xu, et al. 2023. Graph-aware language model pre-training on a large graph corpus can help multiple graph applications. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Dis- covery and Data Mining, pages 5270-5281.
- Tian Yu, Shaolei Zhang, and Yang Feng. 2024. Auto-rag: Autonomous retrieval-augmented generation for large language models. arXiv preprint arXiv:2411.19443. · arXiv
- Tongtao Zhang, Heng Ji, and Avirup Sil. 2019. Joint entity and event extraction with generative adversarial imitation learning. Data Intelligence, 1(2):99-120.
- Siyun Zhao, Yuqing Yang, Zilong Wang, Zhiyuan He, Luna K Qiu, and Lili Qiu. 2024. Retrieval augmented generation (rag) and beyond: A comprehensive survey on how to make your llms use external data more wisely. arXiv preprint arXiv:2409.14924. · arXiv
- Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Huajun Chen, and Ningyu Zhang. 2024. Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities. World Wide Web, 27(5):58.
Cited by
Sorted by citations
Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
Hu, Y., Liu, J., Tan, J., Zhu, Y., & Dou, Z. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1123
- Authors
- Yang, Z., Wang, Y., Shi, Z., Yao, Y., Liang, L., Ding, K., Yilmaz, E., Chen, H., & Zhang, Q.
- Affiliations
- Zhejiang University (CN)
- University College London (GB)
- Ant Group (China) (CN)
- Venue
- Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2025
- Pages
- 16967-16979
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4412945116
- Cited by
- 8
- References
- 1
- Citations by year
- 2026: 8
- FWCI
- 5.62
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Ningbo (2024J020)
- Natural Science Foundation of Zhejiang Province (LQ24F020007)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- event knowledge graph, large language models, event knowledge, knowledge graph retrieval
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
