统一构建知识图谱、事件图谱和常识图谱，提升多类型知识生成能力。
GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction
- 基于三阶段课程学习，融合三类知识图谱数据微调大模型
- 在域内、域外及跨任务数据上均实现性能提升
- 适合需要多类型知识支持的NLP应用开发
广义知识图谱（GKG）包括知识图谱、事件知识图谱和常识知识图谱，是自然语言处理诸多任务的基础。现有研究通常分别构建这三类图谱，忽视了整体洞察与潜在统一性带来的计算资源和应用视角优势。本研究提出一种统一框架以应对任务差异带来的挑战。首先，从29个数据集的15个子任务中收集数据，并划分为样本内、跨任务和分布外（OOD）三类。随后，设计三阶段课程学习微调框架，逐步将三类图谱的知识注入大语言模型。大量实验表明，该模型在三类图谱的构建任务中，均在域内、域外及跨任务数据上表现更优。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。