Narrative stories are characterised by their extended length and depth. They consist of elements such as the viewpoint or perspective from which the story is told, the characters involved, and events that happened. All of these come together to create a cohesive plot, whether it is in a book, a movie, or other form of storytelling. Narrative understanding involves comprehending these elements, how they connect or influence each other, how the relationships between the characters change over time, how events cause other events to happen, and how events are interwoven to shape the narrative’s progression.
LLMs have demonstrated their impressive capabilities in generating human-like language. However, using LLMs for narratives understanding faces several challenges. For example, LLMs have a difficulty in dealing with long narrative text. Events or characters introduced early on in a narrative may have a significant impact on later events. Also, relationships among characters are not fixed and may evolve over time. LLMs may struggle to monitor and capture these evolving relationships. Furthermore, narratives often involve causal relationships among events, characters, and actions. Extracting and correctly inferring these causal links can be challenging for LLMs, as it requires understanding not only what happened but also why and how events are connected. Narrative understanding also requires the ability of inferring the emotional states of characters, their motivations and intentions. This requires LLMs to possess the Theory of Mind (ToM) capabilities. The question of whether LLMs can be trained to develop such ToM capabilities remains open. Another challenging task for LLMs is to accurately extract plots from complex narratives, where they can have plots with multiple storylines, flashbacks, or non-linear structures. Identifying and presenting storylines in a coherent manner can be a significant challenge for LLMs.
Event-Centric Framework for Natural Language Understanding (Jan 2021-Dec 2025), Turing AI Fellowship, funded by the UKRI.
Character-Centric Narrative Understanding, (2023-2027), funded by EPSRC ICASE, with Huawei London Research Centre.
A Lebesgue Integral based Approximation for Language Modelling (2023-2025), funded by the EPSRC.
Our project aims are:
Character-centric analysis. We aim to develop automated approaches for identifying key characters, their roles, characteristics, and relationships within a narrative. This involves tackling challenges such as character co-referencing and linking. Also, detecting relationships among characters may require addressing conflict and incomplete information in narratives and tracking dynamic character relationships.
Story map extraction. Traditionally, events in a storyline usually follow a chronological order. However, in narratives, stories are complex. Narrative could be structured in many ways including flashbacks, multiple stories happening simultaneously, many smaller stories taking place within a bigger plot, or even interwoven stories. We aim to develop automated approaches for story map extraction.
Reasoning in narratives. We aim to enhance LLMs’ capabilities to reason about the temporal order of events and their relationships in narratives. We will also explore approaches to enable LLMs to understanding cause-and-effect relationships and perform theory-of-mind reasoning within narratives.
Interactive narrative understanding. We will investigate a framework for interactive narrative understanding, which will involve a few key components, including (1) Agents – extracting comprehensive character-centric memory from narratives, including aspects such as character’s personal traits and preferences, beliefs and desires, their relationships with other characters, their emotional states, their past behaviours, and their anticipated actions. (2) Settings – identifying character locations and settings, which are often vaguely defined unless crucial to the plot. (3) Responses – ensuring consistency and engagement in user interactions, despite varying user inputs.
Narrative understanding can find a wide variety of applications. Some example applications are listed below:
Personalised interactive narrative storytelling. Creating immersive and interactive narrative environments tailored to individual preferences, resembling the dynamic storylines experienced by individuals, as depicted in the TV series “Westworld”.
ESG report analysis. Deriving insights from lengthy ESG reports, which convey comprehensive and data-driven narratives about companies’ performance and initiatives related to environmental sustainability, social responsibility, and corporate governance.
News storyline generation. In platforms like news aggregators, narrative understanding could improve content relevance and engagement by generating more coherent and informative news storylines.
Consistent and long-range conversations with LLM chatbots. Long conversations with LLM-based chatbots can be considered as a form of narrative storytelling, although it is interactive and dynamically generated. Such long-range conversations that involve diverse topics presents a challenge for conventional methods, as they struggle to effectively address the issue of retaining contextual coherence over long stretches of discourse.
Lin Gui, Jiazheng Li, Junru Lu, Gabriele Pergola, Zhaoyue, Sun, Xingwei Tan, Xinyu, Wang, Hainiu Xu, Wenjia Zhang, Runcong Zhao, Yuxiang Zhou, Lixing Zhu, Qinglin Zhu, Yulan He
H. Xu, S. Qi, J. Li, Y. Zhou, J. Du, C. Catmur and Y. He. EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States. arXiv:2503.03340, 2025.
J. Lu, J. Li, G. Shen, L. Gui, S. An, Y. He, D. Yin and X. Sun. RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following. arXiv:2502.11387, 2025.
Y. Zhang, Y. He and D. Zhou. Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models. arXiv:2503.00449, 2025.
X. Tan, Y. Zhou, G. Pergola and Y. He. Cascading Large Language Models for Salient Event Graph Generation. 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025.
L. Zhu, J. Wang and Y. He. LLMLink: Dual LLMs for Dynamic Entity Linking on Long Narratives with Collaborative Memorisation and Prompt Optimisation. The 31st International Conference on Computational Linguistics (COLING), 2025.
Q. Zhu, R. Zhao, J. Du, L. Gui and Y. He. PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games. arXiv:2404.17662, 2024.
X. Tan, Y. Zhou, G. Pergola and Y. He. Cascading Large Language Models for Salient Event Graph Generation. arXiv:2406.18449, 2024.
H. Xu, R. Zhao, L. Zhu, J. Du, Y. He. OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models. arXiv:2402.06044, 2024. [Website] [Dataset]
R. Zhao, Q. Zhu, H. Xu, J. Li, Y. Zhou, Y. He, and L. Gui. Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives. Findings of ACL, 2024.
X. Tan, Y. Zhou, G. Pergola and Y. He. Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation. 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
R. Zhao, W. Zhang, J. Li, L. Zhu, Y. Li, Y. He and L. Gui. NarrativePlay: Interactive Narrative Understanding. The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Malta, Mar. 2024.
R. Zhao, W. Zhang, J. Li, L. Zhu, Y. Li, Y. He and L. Gui. NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing. The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
X. Wang, L. Gui and Y. He. A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports, The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, Dec. 2023.
L. Zhu, R. Zhao, L. Gui and Y. He. Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding, Findings of EMNLP, 2023.
J. Lu, S. An, M. Lin, G. Pergola, Y. He, D. Yin, X. Sun and Y. Wu. MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation. arXiv preprint arXiv:2308.08239, 2023.
J. Lu, G. Pergola, L. Gui and Y. He. Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering, arXiv:2305.04522.
X. Wang, L. Gui and Y. He. Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization. The 61st Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, Jul. 2023.
X. Tan, G. Pergola and Y. He. Event Temporal Relation Extraction with Bayesian Translational Model. The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL), May 2023.
J. Lu, J. Li, B.C. Wallace, Y. He and G. Pergola. NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization. Findings of EACL, 2023.
H. Li, H. Yan, Y. Li, L. Qian, Y. He and L. Gui. Distinguishability Calibration to In-Context Learning, Findings of EACL, 2023
Z. Sun, J. Li, G. Pergola, B.C. Wallace, B. John, N. Greene, J. Kim and Y. He. PHEE: A Dataset for Pharmacovigilance Event Extraction from Text. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), Dec. 2022.
J. Lu, X. Tan, G. Pergola, L. Gui and Y. He. Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation. Findings of EMNLP, 2022.
H. Yan, L. Gui and Y. He. Hierarchical Interpretation of Neural Text Classification, Computational Linguistics, to appear.
H. Yan, L. Gui, W. Li ad Y. He. Addressing Token Uniformity in Transformers via Singular Value Transformation. 38th Conference on Uncertainty in Artificial Intelligence (UAI), Eindhoven, Netherlands, Aug. 2022.
R. Adewoyin, R. Dutta and Y. He. RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators. 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Jul. 2022.
X. Tan, G. Pergola and Y. He. Extracting Event Temporal Relations via Hyperbolic Geometry. Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 2021.
L. Zhu, G. Pergola, L. Gui, D. Zhou and Y. He. Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection, The 59th Annual Meeting of the Association for Computational Linguistics (ACL), Aug. 2021.
L. Zhang, D. Zhou, Y. He and Z. Yang. MERL: Multimodal Event Representation Learning in Heterogeneous Embedding Spaces, The 35th AAAI Conference on Artificial Intelligence (AAAI), Feb. 2021.
R. Wang, D. Zhou and Y. He. Open Event Extraction from Online Texts using a Generative Adversarial Network. Conference on Empirical Methods in Natural Language Processing (EMNLP), Hong Kong, China, Nov. 2019.
D. Zhou, L. Guo and Y. He. Neural Storyline Extraction Model for Storyline Generation from News Articles, The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), New Orleans, Louisiana, USA, Jun. 2018.