Saved in:
Bibliographic Details
Main Authors: Ye, Hongbin, Gui, Honghao, Zhang, Aijia, Liu, Tong, Jia, Weiqiang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.03022
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915026717114368
author Ye, Hongbin
Gui, Honghao
Zhang, Aijia
Liu, Tong
Jia, Weiqiang
author_facet Ye, Hongbin
Gui, Honghao
Zhang, Aijia
Liu, Tong
Jia, Weiqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03022
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction
Ye, Hongbin
Gui, Honghao
Zhang, Aijia
Liu, Tong
Jia, Weiqiang
Artificial Intelligence
Computation and Language
Machine Learning
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.
title Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2312.03022