Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction
arXiv:2312.03022
Abstract
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.
Accepted by CCKS 2024, best english candidate paper