analiza aiqbench
Narrative Knowledge Weaver (NKW) addresses a critical gap in retrieval-augmented generation by explicitly modeling story-world dynamics, such as evolving character states and causal triggers, rather than treating evidence as isolated chunks. This source-grounded framework demonstrates superior performance on screenplay-level QA benchmarks by aligning textual evidence with canonical graph structures and narrative tools. For developers building long-form reasoning systems, the architecture offers a robust approach to handling complex temporal and causal dependencies inherent in evolving narratives.
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
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. 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.
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. 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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2606.05724 [cs.CL]
(or arXiv:2606.05724v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.05724 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 243 cuvinte
Subiecte conexe
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
arXiv · 17 iun. 2026
MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry
arXiv · 16 iun. 2026
Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models
arXiv · 25 aug. 2026
PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models
arXiv · 15 oct. 2026