Large Language Models (LLMs) can generate creative and engaging narratives from user-specified input, but maintaining coherence and emotional depth throughout these AI-generated stories remains a challenge. In this work, we propose SCORE, a framework for Story Coherence and Retrieval Enhancement, designed to detect and resolve narrative inconsistencies. By tracking key item statuses and generating episode summaries, SCORE uses a Retrieval-Augmented Generation (RAG) approach to identify related episodes and enhance the overall story structure. Experimental results from testing multiple LLM-generated stories demonstrate that SCORE significantly improves the consistency and stability of narrative coherence compared to baseline GPT models, providing a more robust method for evaluating and refining AI-generated narratives.
@article{arxiv.2503.23512,
title = {SCORE: Story Coherence and Retrieval Enhancement for AI Narratives},
author = {Qiang Yi and Yangfan He and Jianhui Wang and Xinyuan Song and ShiYao Qian and Xinhang Yuan and Yi Xin and Yijin Wang and Jingqun Tang and Yuchen Li and Junjiang Lin and Hongyang He and Zhen Tian and Tianxiang Xu and Keqin Li and Kuan Lu and Menghao Huo and Jiaqi Chen and Miao Zhang and Tianyu Shi and Jianyuan Ni},
journal= {arXiv preprint arXiv:2503.23512},
year = {2025}
}