Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Education

TL;DR

This paper presents Graphfusion, a zero-shot framework for constructing knowledge graphs from free text, which improves global triplet fusion and is validated in educational NLP tasks with superior accuracy and human evaluation scores.

Contribution

Introduction of Graphfusion, a novel zero-shot knowledge graph construction framework that enhances global triplet fusion, conflict resolution, and is validated in NLP education scenarios.

Findings

Graphfusion outperforms supervised baselines by up to 10% in link prediction accuracy.

Achieves high human evaluation scores of 2.92/3 for concept extraction.

Demonstrates effective knowledge graph construction in educational NLP applications.

Abstract

Knowledge graphs (KGs) are crucial in the field of artificial intelligence and are widely applied in downstream tasks, such as enhancing Question Answering (QA) systems. The construction of KGs typically requires significant effort from domain experts. Recently, Large Language Models (LLMs) have been used for knowledge graph construction (KGC), however, most existing approaches focus on a local perspective, extracting knowledge triplets from individual sentences or documents. In this work, we introduce Graphusion, a zero-shot KGC framework from free text. The core fusion module provides a global view of triplets, incorporating entity merging, conflict resolution, and novel triplet discovery. We showcase how Graphusion could be applied to the natural language processing (NLP) domain and validate it in the educational scenario. Specifically, we introduce TutorQA, a new expert-verified benchmark for graph reasoning and QA, comprising six tasks and a total of 1,200 QA pairs. Our evaluation demonstrates that Graphusion surpasses supervised baselines by up to 10% in accuracy on link prediction. Additionally, it achieves average scores of 2.92 and 2.37 out of 3 in human evaluations for concept entity extraction and relation recognition, respectively.