让AI理解长篇故事中的角色、时间与因果关系，提升连贯推理能力。
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
- 用叙事结构整合文本与知识图谱，构建可推理的故事世界
- 在多个长篇故事问答数据集上表现最优，尤其擅长角色与时间线推理
- 适合需要深度理解复杂剧情的应用，如剧本分析或智能教育
长篇叙事问答需对不断变化的故事世界进行推理，而非孤立段落：答案可能依赖早期目标、角色状态变化、社会关系、因果触发、时间位置及后续影响。现有检索与图增强生成方法虽提升证据获取，但其单元（片段、实体、关系、摘要或工具动作）未能直接体现证据在故事中的作用。我们提出叙事知识编织者（Narrative Knowledge Weaver, NKW），一种源基框架，对齐文本证据、原子事实、标准图结构、实体档案、互动、情节与叙事主线。查询时，NKW结合文本、图谱与叙事工具，通过后检索阅读技能整合证据，并审计角色、范围、极性、状态与时间约束。在STAGE、FairytaleQA与QuALITY数据集上，NKW在剧本级故事世界问答中表现最强，同时在更侧重段落的基准上仍具竞争力。消融实验、题型分析、图资产统计与案例研究显示，其在角色、场景、时间、因果与叙事进展推理中均有互补优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。