GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction
This addresses the problem of fragmented GKG construction for natural language processing tasks, offering a holistic approach that is incremental in unifying existing methods.
The study tackled the challenge of constructing Generalized Knowledge Graphs (GKG) by proposing a unified framework that integrates knowledge graph, event knowledge graph, and commonsense knowledge graph construction, showing improvements across in-domain, out-of-distribution, and counter-task data.
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.