CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
This work addresses the challenge of nuanced character relation extraction for narrative analysis, benefiting entertainment, publishing, and education sectors, though it appears incremental as it builds on existing LLM methods.
The paper tackles the problem of extracting character relations from long-form narratives by introducing CREFT, a sequential multi-agent LLM framework, which significantly outperforms single-agent LLM baselines in accuracy and completeness on a Korean drama dataset.
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.