arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03022cs.AIcs.CLcs.LG
收藏

超越孤立:多智能体协同提升知识图谱构建

Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction

Zhejiang Lab(之江实验室);Ant Group(蚂蚁集团)

Hongbin Ye, Honghao Gui, Aijia Zhang, Tong Liu, Weiqiang Jia

AI总结:

本文提出多智能体协同框架CooperKGC,通过组建可并行处理实体、关系与事件抽取的协作网络,突破大语言模型在知识图谱构建中的孤立式方法,并在多轮交互中提升知识选择、修正与聚合能力。

摘要:

本文提出CooperKGC,一个挑战大语言模型(LLMs)在知识图谱构建(KGC)中传统孤立式方法的新框架。CooperKGC建立协作处理网络,组建能够同时处理实体、关系和事件抽取任务的团队。实验表明,在CooperKGC中促进协作能够在多轮交互中增强知识选择、修正和聚合能力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑