# Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding

arXiv: https://arxiv.org/abs/2606.05724 · HTML: https://mlsanity.com/paper/2606.05724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [Knowledge Graph-Guided Retrieval Augmented Generation](https://mlsanity.com/paper/2502.06864/) (2025)
- [Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution](https://mlsanity.com/paper/1906.01753/) (2019)
- [A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces](https://mlsanity.com/paper/2602.03442/) (2026)
- [Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling](https://mlsanity.com/paper/2009.11032/) (2020)
- [Event Causality Is Key to Computational Story Understanding](https://mlsanity.com/paper/2311.09648/) (2023)
- [EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs](https://mlsanity.com/paper/2404.00209/) (2024)
- [STAGE: A Full-Screenplay Benchmark for Reasoning over Evolving Stories](https://mlsanity.com/paper/2601.08510/) (2026)

## Abstract (arXiv)

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. Existing retrieval and graph-augmented generation methods improve evidence access, but their units--chunks, entities, relations, summaries, or tool actions--do not directly encode how evidence functions in a story. We introduce Narrative Knowledge Weaver(NKW), a source-grounded framework that aligns textual evidence, atomic facts, canonical graph structure, entity profiles, interactions, episodes, and storylines. At query time, NKW uses text, graph, and narrative tools with post-retrieval reading skills to assemble evidence and audit actor, scope, polarity, state, and temporal constraints. Across STAGE, FairytaleQA, and QuALITY, NKW is strongest on screenplay-level story-world QA while remaining competitive on more passage-centered benchmarks. Ablations, question-type analyses, graph-asset statistics, and case studies show complementary benefits for character, scene, temporal, causal, and narrative-progression reasoning.