用多智能体协作提取复杂角色关系，提升剧本文本分析效率。
CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
- 分步构建角色图谱，通过智能体迭代优化关系与角色归属
- 在韩剧数据集上准确率和完整度显著优于单智能体方法
- 适合影视编剧、出版编辑及教育领域快速理解复杂叙事
理解复杂角色关系对叙事分析和剧本评估至关重要，但现有方法难以处理长篇叙事中的微妙互动。为此，我们提出CREFT，一种基于专用大语言模型智能体的序列化框架。首先通过知识蒸馏构建基础角色图谱，随后迭代优化角色构成、关系抽取、角色识别与群体分配。在自建韩剧数据集上的实验表明，CREFT在准确率和完整性上均显著超越单智能体基线。通过系统化可视化角色网络，CREFT有效简化叙事理解，加速剧本审查，为娱乐、出版和教育领域带来显著价值。
原文摘要 · Abstract (English)
Understanding complex character relations is crucial for narrative analysis and efficient script evaluation, yet existing extraction methods often fail to handle long-form narratives with nuanced interactions. To address this challenge, we present CREFT, a novel sequential framework leveraging specialized Large Language Model (LLM) agents. First, CREFT builds a base character graph through knowledge distillation, then iteratively refines character composition, relation extraction, role identification, and group assignments. Experiments on a curated Korean drama dataset demonstrate that CREFT significantly outperforms single-agent LLM baselines in both accuracy and completeness. By systematically visualizing character networks, CREFT streamlines narrative comprehension and accelerates script review -- offering substantial benefits to the entertainment, publishing, and educational sectors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。