# Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions

arXiv: https://arxiv.org/abs/2402.13551 · HTML: https://mlsanity.com/paper/2402.13551/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 66 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [Linguistically-Informed Self-Attention for Semantic Role Labeling](https://mlsanity.com/paper/1804.08199/) (2018)
- [Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers](https://mlsanity.com/paper/2305.15805/) (2023)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Revealing the Myth of Higher-Order Inference in Coreference Resolution](https://mlsanity.com/paper/2009.12013/) (2020)
- [Inquisitive Question Generation for High Level Text Comprehension](https://mlsanity.com/paper/2010.01657/) (2020)
- [TellMeWhy: A Dataset for Answering Why-Questions in Narratives](https://mlsanity.com/paper/2106.06132/) (2021)
- [Neural Discourse Structure for Text Categorization](https://mlsanity.com/paper/1702.01829/) (2017)
- [Personality Understanding of Fictional Characters during Book Reading](https://mlsanity.com/paper/2305.10156/) (2023)
- [Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections](https://mlsanity.com/paper/2111.00701/) (2021)
- [Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind](https://mlsanity.com/paper/2211.04684/) (2022)
- [QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing](https://mlsanity.com/paper/2310.14520/) (2023)
- [RELIC: Retrieving Evidence for Literary Claims](https://mlsanity.com/paper/2203.10053/) (2022)
- [A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents](https://mlsanity.com/paper/2305.14772/) (2023)
- [Elaborative Simplification as Implicit Questions Under Discussion](https://mlsanity.com/paper/2305.10387/) (2023)

## Built on by (most cited first, 11 of 11)

- [CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving](https://mlsanity.com/paper/2404.17729/) (2024)
- [The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters](https://mlsanity.com/paper/2501.01705/) (2025)
- [SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension](https://mlsanity.com/paper/2508.01959/) (2025)
- [Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding](https://mlsanity.com/paper/2512.17220/) (2025)
- [HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling](https://mlsanity.com/paper/2512.23959/) (2025)
- [DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph](https://mlsanity.com/paper/2410.14666/) (2024)
- [Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings](https://mlsanity.com/paper/2506.08592/) (2025)
- [Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models](https://mlsanity.com/paper/2507.09506/) (2025)
- [A Survey of QUD Models for Discourse Processing](https://mlsanity.com/paper/2502.15573/) (2025)
- [Literary Evidence Retrieval via Long-Context Language Models](https://mlsanity.com/paper/2506.03090/) (2025)
- [GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study](https://mlsanity.com/paper/2605.28643/) (2026)

## Abstract (arXiv)

This work introduces an original and practical paradigm for narrative comprehension, stemming from the characteristics that individual passages within narratives tend to be more cohesively related than isolated. Complementary to the common end-to-end paradigm, we propose a fine-grained modeling of narrative context, by formulating a graph dubbed NarCo, which explicitly depicts task-agnostic coherence dependencies that are ready to be consumed by various downstream tasks. In particular, edges in NarCo encompass free-form retrospective questions between context snippets, inspired by human cognitive perception that constantly reinstates relevant events from prior context. Importantly, our graph formalism is practically instantiated by LLMs without human annotations, through our designed two-stage prompting scheme. To examine the graph properties and its utility, we conduct three studies in narratives, each from a unique angle: edge relation efficacy, local context enrichment, and broader application in QA. All tasks could benefit from the explicit coherence captured by NarCo.