SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916953879216128 |
|---|---|
| author | Yi, Qiang He, Yangfan Wang, Jianhui Song, Xinyuan Qian, ShiYao Yuan, Xinhang Xin, Yi Wang, Yijin Tang, Jingqun Li, Yuchen Lin, Junjiang He, Hongyang Tian, Zhen Xu, Tianxiang Li, Keqin Lu, Kuan Huo, Menghao Chen, Jiaqi Zhang, Miao Shi, Tianyu Ni, Jianyuan |
| author_facet | Yi, Qiang He, Yangfan Wang, Jianhui Song, Xinyuan Qian, ShiYao Yuan, Xinhang Xin, Yi Wang, Yijin Tang, Jingqun Li, Yuchen Lin, Junjiang He, Hongyang Tian, Zhen Xu, Tianxiang Li, Keqin Lu, Kuan Huo, Menghao Chen, Jiaqi Zhang, Miao Shi, Tianyu Ni, Jianyuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23512 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCORE: Story Coherence and Retrieval Enhancement for AI Narratives Yi, Qiang He, Yangfan Wang, Jianhui Song, Xinyuan Qian, ShiYao Yuan, Xinhang Xin, Yi Wang, Yijin Tang, Jingqun Li, Yuchen Lin, Junjiang He, Hongyang Tian, Zhen Xu, Tianxiang Li, Keqin Lu, Kuan Huo, Menghao Chen, Jiaqi Zhang, Miao Shi, Tianyu Ni, Jianyuan Computation and Language 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. |
| title | SCORE: Story Coherence and Retrieval Enhancement for AI Narratives |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.23512 |