Graph-Augmented Relation Extraction Model with LLMs-Generated Support Document

TL;DR

This paper presents a novel relation extraction method that combines Large Language Models and Graph Neural Networks to generate enriched context and improve understanding of complex inter-entity relationships across sentences.

Contribution

It introduces a new approach integrating LLM-generated support documents with GNNs for enhanced sentence-level relation extraction.

Findings

Improved relation extraction accuracy on CrossRE dataset

Effective integration of LLMs and GNNs for contextual understanding

Enhanced modeling of inter-entity interactions across sentences

Abstract

This study introduces a novel approach to sentence-level relation extraction (RE) that integrates Graph Neural Networks (GNNs) with Large Language Models (LLMs) to generate contextually enriched support documents. By harnessing the power of LLMs to generate auxiliary information, our approach crafts an intricate graph representation of textual data. This graph is subsequently processed through a Graph Neural Network (GNN) to refine and enrich the embeddings associated with each entity ensuring a more nuanced and interconnected understanding of the data. This methodology addresses the limitations of traditional sentence-level RE models by incorporating broader contexts and leveraging inter-entity interactions, thereby improving the model's ability to capture complex relationships across sentences. Our experiments, conducted on the CrossRE dataset, demonstrate the effectiveness of our approach, with notable improvements in performance across various domains. The results underscore the potential of combining GNNs with LLM-generated context to advance the field of relation extraction.