Elamur Research⌕
☰
home / papers / 2026 / EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems

EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems

Paper · 2026 · Zhengyi Zhao, Shubo Zhang, Yiming Du et al.

Summary

LLM-based dialogue systems often handle each turn on its own and miss the event structure behind a conversation. EventWeave addresses this by building an event graph that grows as the dialogue unfolds. It separates core events (the main goal, such as attending a festival) from supporting events (related details, such as past concerts or schedule clashes).

The pipeline works in four steps:

  • A BERT-based encoder with a binary classifier flags turns that contain events.
  • Similar events are clustered into nodes.
  • Nodes are linked by three edge types, and finished segments are compressed into summary nodes, forming a hierarchy.
  • When replying, multi-head attention scores each node against the current query. The selected structure is written into the LLM prompt, so no graph neural network is needed.

On Conversation Chronicle (CC), MSC and LoCoMo, the method produced more natural and relevant replies than baselines. It also needed less computation than feeding in the full history. Ablations attribute the gains to modelling event relations, not to packing in more content. This matters for long, multi-session assistants.

Key points

  • Three relation types: sequential edges (turn order), temporal edges (explicit time expressions like "yesterday") and reasoning links (cosine similarity above a threshold θ). Event clusters are formed with a separate threshold δ.
  • Event detection: the encoder is fine-tuned on DailyDialog and OpenDialKG. The generating LLM itself is not fine-tuned on domain data.
  • Clustering ablation: removing event clustering lowered response relevance scores by 27%.
  • Dialogue length: test dialogues were grouped as 5–10, 11–20, 21–30 and 31+ turns. Vanilla GPT-4o got worse as dialogues lengthened, while EventWeave improved. Performance stays strong up to about 35 turns, after which pruning keeps the cost manageable.
  • Datasets: the evaluation uses CC, MSC and LoCoMo, although the conclusion mentions only "two" benchmarks, which is an inconsistency in the paper. An MSC case study (a missing cat that returns, plus its liking for tuna) shows how core and supporting events are combined in a reply.

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

🎓Chinese University of Hong KongHong Kong · China159 works · 16,154 citations🏢Huawei TechnologiesShenzhen · China96 works · 15,432 citations🎓University of International RelationsBeijing · China4 works · 1 citation

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 654 works

Cite

Cite as Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li and Kam-Fai Wong. 2026. EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems. Proceedings of the 64th 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/v1/2026.acl-long.198

@inproceedings{zhao2026eventweave,
  title = {{EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems}},
  author = {Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li and Kam-Fai Wong},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.198},
  url = {https://doi.org/10.18653/v1/2026.acl-long.198}
}

References

38 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Vladimir Araujo, Alvaro Soto, and Marie-Francine Moens. 2023. A memory model for question answering from streaming data supported by rehearsal and anticipation of coreference information. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13124–13138, Toronto, Canada. Asso… find
  2. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, et al. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conference on Artifici… find
  3. Howard Chen, Ramakanth Pasunuru, Jason Weston, and Asli Celikyilmaz. 2023. Walking down the memory maze: Beyond context limit through interactive reading. Preprint, arXiv:2310.05029. — [arXiv:2310.05029](https://arxiv.org/abs/2310.05029) find
  4. Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, and Tat-Seng Chua. 2023. Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non-collaboration. Preprint, arXiv:2305.13626.
  5. Yiming Du, Hongru Wang, Zhengyi Zhao, Bin Liang, Baojun Wang, Wanjun Zhong, Zezhong Wang, and Kam-Fai Wong. 2024. PerLTQA: A personal long-term memory dataset for memory classification, retrieval, and fusion in question answering. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Proces… find
  6. Mauajama Firdaus, Nidhi Thakur, and Asif Ekbal. 2021. Aspect-aware response generation for multimodal dialogue system. ACM Transactions on Intelligent Systems and Technology (TIST), 12(2):1–33. find
  7. Janghoon Han, Taesuk Hong, Byoungjae Kim, Youngjoong Ko, and Jungyun Seo. 2021. Fine-grained post-training for improving retrieval-based dialogue systems. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies… find
  8. Yongquan He, Peng Zhang, Luchen Liu, Qi Liang, Wenyuan Zhang, and Chuang Zhang. 2024. Hip network: Historical information passing network for extrapolation reasoning on temporal knowledge graph. arXiv preprint arXiv:2402.12074. — [arXiv:2402.12074](https://arxiv.org/abs/2402.12074) find
  9. Kai Tzu iunn Ong, Namyoung Kim, Minju Gwak, Hyungjoo Chae, Taeyoon Kwon, Yohan Jo, Seung won Hwang, Dongha Lee, and Jinyoung Yeo. 2025. Towards lifelong dialogue agents via timeline-based memory management. Preprint, arXiv:2406.10996. find
  10. Jihyoung Jang, Minseong Boo, and Hyounghun Kim. 2023. Conversation chronicles: Towards diverse temporal and relational dynamics in multi-session conversations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13584–13606, Singapore. Association for Com… find
  11. Jihyoung Jang, Taeyoung Kim, and Hyounghun Kim. 2024. Mixed-session conversation with egocentric memory. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11786– 11815. find
  12. Hideaki Joko, Shubham Chatterjee, Andrew Ramsay, Arjen P De Vries, Jeff Dalton, and Faegheh Hasibi. 2024. Doing personal laps: Llm-augmented dialogue construction for personalized multi-session conversational search. In Proceedings of the 47th International ACM SIGIR Conference on Research and Devel… find
  13. Eunwon Kim, Chanho Park, and Buru Chang. 2025. Share: Shared memory-aware open-domain long-term dialogue dataset constructed from movie script. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14474–14498. find
  14. Frederic Kirstein, Jan Philip Wahle, Bela Gipp, and Terry Ruas. 2025. Cads: A systematic literature review on the challenges of abstractive dialogue summarization. Journal of Artificial Intelligence Research, 82:313–365. find
  15. Kaj U Koskinen, Rainer Breite, Kaj U Koskinen, and Rainer Breite. 2020. Process philosophy. Uninterrupted Knowledge Creation: Process Philosophy and Autopoietic Perspectives, pages 13–24. find
  16. Arnold B Levison. 1987. Events and time’s flow. Mind, 96(383):341–353. find
  17. Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, and Tat-Seng Chua. 2024. Hello again! llm-powered personalized agent for long-term dialogue. arXiv preprint arXiv:2406.05925.
  18. Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, and Tat-Seng Chua. 2025. Hello again! llm-powered personalized agent for long-term dialogue. Preprint, arXiv:2406.05925.
  19. Juntao Li, Chang Liu, Chongyang Tao, Zhangming Chan, Dongyan Zhao, Min Zhang, and Rui Yan. 2021. Dialogue history matters! personalized response selection in multi-turn retrieval-based chatbots. ACM Transactions on Information Systems (TOIS), 39(4):1– 25. find
  20. Ang Lv, Jinpeng Li, Yuhan Chen, Gao Xing, Ji Zhang, and Rui Yan. 2023. DialoGPS: Dialogue path sampling in continuous semantic space for data augmentation in multi-turn conversations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… find
  21. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of llm agents. Preprint, arXiv:2402.17753. find
  22. Tzu-iunn Ong, Namyoung Kim, Minju Gwak, Hyungjoo Chae, Taeyoon Kwon, Yohan Jo, Seung-won Hwang, Dongha Lee, Jinyoung Yeo, et al. 2024. Towards lifelong dialogue agents via relation-aware memory construction and timeline-augmented response generation. arXiv e-prints, pages arXiv–2406. find
  23. Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, and Zaid Harchaoui. 2021. Mauve: Measuring the gap between neural text and human text using divergence frontiers. Advances in Neural Information Processing Systems, 34:4816–4828.
  24. Hiromasa Sakurai and Yusuke Miyao. 2024. Evaluating intention detection capability of large language models in persuasive dialogues. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1635–1657, Bangkok, Thailand. Association for… find
  25. Quan Tu, Chongyang Tao, and Rui Yan. 2024. Multi-grained conversational graph network for retrieval-based dialogue systems. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11756–11765. find
  26. Yi-Lin Tuan, Sajjad Beygi, Maryam Fazel-Zarandi, Qiaozi Gao, Alessandra Cervone, and William Yang Wang. 2022. Towards large-scale interpretable knowledge graph reasoning for dialogue systems. In Findings of the Association for Computational Linguistics: ACL 2022, pages 383–395. find
  27. Deeksha Varshney, Niranshu Behera, Prajeet Katari, and Asif Ekbal. 2025. Medprom: Bridging dialogue gaps in healthcare with knowledge-enhanced generative models. ACM Transactions on Computing for Healthcare. find
  28. Nicholas Thomas Walker, Stefan Ultes, and Pierre Lison. 2022. Graphwoz: Dialogue management with conversational knowledge graphs. arXiv preprint arXiv:2211.12852. — [arXiv:2211.12852](https://arxiv.org/abs/2211.12852) find
  29. Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2023. Augmenting language models with long-term memory. Preprint, arXiv:2306.07174. find
  30. Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu. 2025. Longmemeval: Benchmarking chat assistants on long-term interactive memory. In The Thirteenth International Conference on Learning Representations.
  31. Heng-Da Xu, Xian-Ling Mao, Puhai Yang, Fanshu Sun, and Heyan Huang. 2024. Rethinking task-oriented dialogue systems: From complex modularity to zero-shot autonomous agent. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2748–… find
  32. Jing Xu, Arthur Szlam, and Jason Weston. 2021. Beyond goldfish memory: Long-term open-domain conversation. Preprint, arXiv:2107.07567. find
  33. Shiquan Yang, Rui Zhang, and Sarah Erfani. 2020. GraphDialog: Integrating graph knowledge into end-to-end task-oriented dialogue systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1878–1888, Online. Association for Computational Linguist… find
  34. Congchi Yin, Piji Li, and Zhaochun Ren. 2023. Ctrl-struct: Dialogue structure learning for open-domain response generation. In Proceedings of the ACM web conference 2023, pages 1539–1550. find
  35. Haoyu Zhang, Meng Liu, Zan Gao, Xiaoqiang Lei, Yinglong Wang, and Liqiang Nie. 2021. Multimodal dialog system: Relational graph-based context-aware question understanding. In Proceedings of the 29th ACM international conference on multimedia, pages 695–703. find
  36. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204–2213, Melbou…
  37. Jianan Zhao, Le Zhuo, Yikang Shen, Meng Qu, Kai Liu, Michael Bronstein, Zhaocheng Zhu, and Jian Tang. 2023. Graphtext: Graph reasoning in text space. arXiv preprint arXiv:2310.01089. — [arXiv:2310.01089](https://arxiv.org/abs/2310.01089) find
  38. Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian, and Ji-Rong Wen. 2022. Less is more: Learning to refine dialogue history for personalized dialogue generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tec… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhao-2026-eventweave-dynamic-framework-capturing-core/