CREFT: Sequential Multi-Agent LLM for Character Relation Extraction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chun, Ye Eun, Hwang, Taeyoon, Hwang, Seung-won, Kim, Byung-Hak
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909629300080640
author Chun, Ye Eun
Hwang, Taeyoon
Hwang, Seung-won
Kim, Byung-Hak
author_facet Chun, Ye Eun
Hwang, Taeyoon
Hwang, Seung-won
Kim, Byung-Hak
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
Chun, Ye Eun
Hwang, Taeyoon
Hwang, Seung-won
Kim, Byung-Hak
Computation and Language
Artificial Intelligence
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.
title CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.24553