SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
Yi Qiang, Yangfan He, Jianhui Wang, Xinyuan Song, Xinhang Yuan, Keqin Li, Tianyu Shi, Zhen Chen, Jiaqi Chen, Karen H. Lu, Meimei Huo, Miao Zhang, Zhen Tian, Tianxiang Xu, Keqin Li, Menghao Huo, Jiaqi Chen, Miao Zhang, Tianyu Shi, Jianyuan Ni
Abstract
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.