Evaluating LLM Story Generation through Large-scale Network Analysis of Social Structures
Abstract
Evaluating the creative capabilities of large language models (LLMs) in complex tasks often requires human assessments that are difficult to scale. We introduce a novel, scalable methodology for evaluating LLM story generation by analyzing underlying social structures in narratives as signed character networks. To demonstrate its effectiveness, we conduct a large-scale comparative analysis using networks from over 1,200 stories, generated by four leading LLMs (GPT-4o, GPT-4o mini, Gemini 1.5 Pro, and Gemini 1.5 Flash) and a human-written corpus. Our findings, based on network properties like density, clustering, and signed edge weights, show that LLM-generated stories consistently exhibit a strong bias toward tightly-knit, positive relationships, which aligns with findings from prior research using human assessment. Our proposed approach provides a valuable tool for evaluating limitations and tendencies in the creative storytelling of current and future LLMs.
Keywords
Cite
@article{arxiv.2510.18932,
title = {Evaluating LLM Story Generation through Large-scale Network Analysis of Social Structures},
author = {Hiroshi Nonaka and K. E. Perry},
journal= {arXiv preprint arXiv:2510.18932},
year = {2025}
}
Comments
This paper has 14 pages and 8 figures. To be presented at the NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling