arXiv Open Access 2025

CREFT: Sequential Multi-Agent LLM for Character Relation Extraction

Ye Eun Chun Taeyoon Hwang Seung-won Hwang Byung-Hak Kim
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (4)

Y

Ye Eun Chun

T

Taeyoon Hwang

S

Seung-won Hwang

B

Byung-Hak Kim

Format Sitasi

Chun, Y.E., Hwang, T., Hwang, S., Kim, B. (2025). CREFT: Sequential Multi-Agent LLM for Character Relation Extraction. https://arxiv.org/abs/2505.24553

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓