CREFT: Sequential Multi-Agent LLM for Character Relation Extraction

• URL: http://arxiv.org/abs/2505.24553v1
• Date: Fri, 30 May 2025 13:01:36 GMT
• Title: CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
• Authors: Ye Eun Chun, Taeyoon Hwang, Seung-won Hwang, Byung-Hak Kim,
• Abstract summary: CREFT builds a base character graph through knowledge distillation, then iteratively refines character composition, relation extraction, role identification, and group assignments.<n> Experiments on a curated Korean drama dataset demonstrate that CREFT significantly outperforms single-agent LLM baselines in both accuracy and completeness.
• Score: 17.568992245453224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing [111.06936588273868]
  RMTBench is a comprehensive textbfuser-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.<n>Our benchmark constructs dialogues based on explicit user motivations rather than character descriptions, ensuring alignment with practical user applications.<n>By shifting focus from character background to user intention fulfillment, RMTBench bridges the gap between academic evaluation and practical deployment requirements.
  arXiv  Detail & Related papers  (2025-07-27T16:49:47Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization [0.0]
  We introduce NexusSum, a multi-agent LLM framework for narrative summarization.<n>A narrative-specific preprocessing method standardizes character dialogue and descriptive text into a unified format.<n>Our method establishes a new state-of-the-art in narrative summarization, achieving up to a 30.0% improvement in BERTScore (F1) across books, movies, and TV scripts.
  arXiv  Detail & Related papers  (2025-05-30T13:26:23Z)
• KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing [64.38243807002878]
  We present KnowTrace, an elegant RAG framework to mitigate the context overload in large language models.<n>KnowTrace autonomously traces out desired knowledge triplets to organize a specific knowledge graph relevant to the input question.<n>It consistently surpasses existing methods across three multi-hop question answering benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T17:22:20Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Beyond LLMs: A Linguistic Approach to Causal Graph Generation from Narrative Texts [5.309459419455988]
  We propose a novel framework for generating causal graphs from narrative texts.<n>We introduce an "Expert Index," comprising seven linguistically informed features, integrated into a Situation-Task-Action-Consequence (STAC) classification model.<n> Experiments on 100 narrative chapters and short stories demonstrate that our approach consistently outperforms GPT-4o and Claude 3.5 in causal graph quality.
  arXiv  Detail & Related papers  (2025-04-10T05:09:07Z)
• BookWorm: A Dataset for Character Description and Analysis [59.186325346763184]
  We define two tasks: character description, which generates a brief factual profile, and character analysis, which offers an in-depth interpretation. We introduce the BookWorm dataset, pairing books from the Gutenberg Project with human-written descriptions and analyses. Our findings show that retrieval-based approaches outperform hierarchical ones in both tasks.
  arXiv  Detail & Related papers  (2024-10-14T10:55:58Z)
• Agents' Room: Narrative Generation through Multi-step Collaboration [54.98886593802834]
  We propose a generation framework inspired by narrative theory that decomposes narrative writing into subtasks tackled by specialized agents.<n>We show that Agents' Room generates stories preferred by expert evaluators over those produced by baseline systems.
  arXiv  Detail & Related papers  (2024-10-03T15:44:42Z)
• Enhancing LLM's Cognition via Structurization [41.13997892843677]
  Large language models (LLMs) process input contexts through a causal and sequential perspective. This paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements.
  arXiv  Detail & Related papers  (2024-07-23T12:33:58Z)
• Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives [21.297972871264744]
  We introduce a new benchmark, Conan, designed for extracting and analysing intricate character relation graphs from detective narratives. Specifically, we designed hierarchical relationship categories and manually extracted and annotated role-oriented relationships from the perspectives of various characters. Our experiments with advanced Large Language Models (LLMs) like GPT-3.5, GPT-4, and Llama2 reveal their limitations in inferencing complex relationships and handling longer narratives.
  arXiv  Detail & Related papers  (2024-02-16T19:59:45Z)
• Recurrent Alignment with Hard Attention for Hierarchical Text Rating [6.858867989434858]
  We propose a novel framework for hierarchical text rating utilizing large language models (LLMs) Our framework incorporates Recurrent Alignment with Hard Attention (RAHA) Experimental results demonstrate that RAHA outperforms existing state-of-the-art methods on three hierarchical text rating datasets.
  arXiv  Detail & Related papers  (2024-02-14T00:40:51Z)
• Screenplay Summarization Using Latent Narrative Structure [78.45316339164133]
  We propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays. Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode.
  arXiv  Detail & Related papers  (2020-04-27T11:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.