GKG-LLM：面向广义知识图谱构建的统一框架

GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction

March 14, 2025

作者: Jian Zhang, Bifan Wei, Shihao Qi, haiping Zhu, Jun Liu, Qika Lin

cs.AI

摘要

广义知识图谱（GKG）的构建，包括知识图谱、事件知识图谱和常识知识图谱，是多种自然语言处理任务的基础。当前研究通常分别构建这些类型的图谱，忽视了整体洞察力以及在计算资源和使用视角上可能实现的统一性。然而，开发统一GKG框架的一个关键挑战在于任务特定差异带来的障碍。在本研究中，我们提出了一个构建广义知识图谱的统一框架以应对这一挑战。首先，我们从三类图谱的29个数据集中收集了15个子任务的数据，并将其分类为样本内数据、对抗任务数据和分布外（OOD）数据。随后，我们设计了一个三阶段课程学习微调框架，通过迭代地将三类图谱的知识注入大型语言模型中。大量实验表明，我们提出的模型在域内、OOD及对抗任务数据上均提升了所有三类图谱的构建效果。

English

The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data.