This paper introduces CooperKGC, a novel framework challenging the conventional solitary approach of large language models (LLMs) in knowledge graph construction (KGC). CooperKGC establishes a collaborative processing network, assembling a team capable of concurrently addressing entity, relation, and event extraction tasks. Experimentation demonstrates that fostering collaboration within CooperKGC enhances knowledge selection, correction, and aggregation capabilities across multiple rounds of interactions.

翻译：本文提出CooperKGC，这是一个挑战大型语言模型在知识图谱构建中传统孤立处理方式的新颖框架。CooperKGC建立了一个协同处理网络，组建了一个能够同时处理实体、关系和事件抽取任务的智能体团队。实验表明，在CooperKGC中促进多轮交互内的协作，能有效增强知识选择、校正与聚合能力。