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.
@article{arxiv.2312.03022,
title = {Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction},
author = {Hongbin Ye and Honghao Gui and Aijia Zhang and Tong Liu and Weiqiang Jia},
journal= {arXiv preprint arXiv:2312.03022},
year = {2024}
}
Comments
Accepted by CCKS 2024, best english candidate paper