narratology

该论文结合叙事学与机制可解释性，在GPT-2-Small、Gemma-2-2B和Llama-3.1-8B中识别出与叙事性（narrativity）相关的注意力头、MLP神经元和稀疏自编码器特征，并通过消融实验证明这些组件对模型的叙事行为具有因果影响。

This paper introduces the Narrative World Model (NWM), a memory system for long-form fiction writers that uses narratology-grounded typed temporal-state graphs and query-conditioned hybrid retrieval to answer multi-hop questions about evolving story state. The system significantly outperforms existing temporal-knowledge-graph frameworks like Graphiti on benchmark narratological QA tasks.

The essay argues that literary disciplines provide essential tools for building culturally literate AI, proposing a layered framework to address structural monolingualism and promote pluralistic interpretations of AI textuality.