The paper introduces a modular framework that builds an entity‑interaction graph from narratives without relying on annotated node labels. It uses a domain‑adapted BERT encoder to identify entity spans, constructs a bipartite graph, and classifies it with a Heterogeneous Graph Transformer. By casting the graph as a hypergraph and applying counterfactual distillation, the method estimates the Individual Treatment Effect of each node, pruning extraneous entities to produce a minimal predictive subgraph while maintaining high accuracy on the PAN Oppositional Narratives benchmark.
By Diego Revilla, Martin Fernandez-de-Retana, Lingfeng Chen, Aritz Bilbao-Jayo, Miguel Fernandez-de-Retana
The paper presents a detailed examination of narrative elements—agency, setting, and events—within the Dolma web-scale pretraining corpus. Using a framework of 11 interpretable dimensions, the authors hand‑annotated 400 passages, expanded this to a 25,000‑passage LLM‑labeled dataset, and trained NarraBERT models to predict narrative features across 13 million passages, producing the NarraDolma dataset. The study reveals that narrative structure is measurable at scale and that narrative qualities vary unevenly across different data sources, topics, and formats, highlighting gaps in current data curation practices.
By Teagan Johnson, Elliott Ash, Andrew Piper, Maria Antoniak
arXiv:2602. 15851v2 Announce Type: replace-cross Abstract: Applications of narrative theories using large language models (LLMs) deliver promising methods in automatic story generation and understanding tasks.
By David Y. Liu, Aditya Joshi, Paul Dawson
arXiv:2606. 05724v1 Announce Type: cross Abstract: Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations, causal triggers, temporal position, and later consequences.
By Qiuyu Tian, Fengyi Chen, Yiding Li, Youyong Kong, Fan Guo, Yuyao Li, Jinjing Shen, Zhijing Xie, Yiyun Luo, Xin Zhang, Yingce Xia, Zequn Liu
Do language models carry information about narrative events before writing them, and how far ahead? We examine narrative lookahead through salient, state-changing events rather than tokens or response...
arXiv:2609.38406v1 Announce Type: new
Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mi...
By Eftekhar Hossain, John Salvador, Santu Karmaker
arXiv:2610.27597v1 Announce Type: cross
Abstract: Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely examining concurrently how models...
By Bo Zou, Chao Xu
arXiv:2609.38799v1 Announce Type: new
Abstract: Understanding multi-perspective alternative narratives requires identifying how their information agrees, conflicts, or differs across sources. Existin...
By Eftekhar Hossain, Santu Karmaker
arXiv:2605.27156v2 Announce Type: replace-cross
Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, particularly for long-tail do...
By Ruikang Zhang, Zhanni Chen, Yiqiao Cai, Qi Su
arXiv:2606. 17350v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet the question of whether these models are capable of generating diverse outputs remains contested.
By Thennal DK, Hans Ole Hatzel
arXiv:2607. 05577v1 Announce Type: new Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship shifted.
By Mohammad Saifullah, Thomas Kornmaier, Taaha Kazi, Vasu Sharma, Aditya Sanjiv Kanade, Aanand Kumar Yadav
The paper introduces Critic's Eye, a method for computational motif discovery that models a play as a heterogeneous Narrative Topology Graph and performs discriminative inference over global structural evidence. It achieves 84.8% Hit@5 on a benchmark, nearly quadrupling the performance of large foundation models such as Gemini-3-pro-preview. The authors argue that explicit structural priors outperform mere parameter scaling for decoding the complex architecture of long‑form literature.
By Xinyu Sun, Zhangyue Yin, Xinyi Ju, Xin Wang