Creative Convergence or Imitation? Genre-Specific Homogeneity in LLM-Generated Chinese Literature

TL;DR

This paper analyzes how large language models generate Chinese literature, revealing they often produce homogeneous stories due to limited understanding of narrative functions, and introduces a new theoretical framework for analysis.

Contribution

It proposes a novel narrative analysis framework combining Proppian narratology with modern web narrative structures, specifically tailored for LLM-generated Chinese literature.

Findings

LLMs produce structurally homogenized stories with stereotypical resolutions.

Current LLMs struggle to correctly understand narrative functions.

Homogeneity arises from rigid narrative generation paradigms.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in narrative generation. However, they often produce structurally homogenized stories, frequently following repetitive arrangements and combinations of plot events along with stereotypical resolutions. In this paper, we propose a novel theoretical framework for analysis by incorporating Proppian narratology and narrative functions. This framework is used to analyze the composition of narrative texts generated by LLMs to uncover their underlying narrative logic. Taking Chinese web literature as our research focus, we extend Propp's narrative theory, defining 34 narrative functions suited to modern web narrative structures. We further construct a human-annotated corpus to support the analysis of narrative structures within LLM-generated text. Experiments reveal that the primary reasons for the singular narrative logic and severe homogenization in generated texts are that current LLMs are unable to correctly comprehend the meanings of narrative functions and instead adhere to rigid narrative generation paradigms.