Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction

TL;DR

This paper introduces an innovative, scalable method for knowledge graph construction using iterative zero-shot prompting of large language models like GPT-3.5, eliminating the need for human expertise or external resources.

Contribution

It presents a novel iterative zero-shot prompting strategy for LLMs to generate knowledge graphs without external data or examples, enhancing scalability and versatility.

Findings

Effective extraction of knowledge graph components demonstrated

Zero-shot prompting achieves comparable results without training data

Scalable approach applicable across different domains

Abstract

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast amount of information in a properly interconnected and interpretable structure. However, their generation is still challenging and often requires considerable human effort and domain expertise, hampering the scalability and flexibility across different application fields. This paper proposes an innovative knowledge graph generation approach that leverages the potential of the latest generative large language models, such as GPT-3.5, that can address all the main critical issues in knowledge graph building. The approach is conveyed in a pipeline that comprises novel iterative zero-shot and external knowledge-agnostic strategies in the main stages of the generation process. Our unique manifold approach may encompass significant benefits to the scientific community. In particular, the main contribution can be summarized by: (i) an innovative strategy for iteratively prompting large language models to extract relevant components of the final graph; (ii) a zero-shot strategy for each prompt, meaning that there is no need for providing examples for "guiding" the prompt result; (iii) a scalable solution, as the adoption of LLMs avoids the need for any external resources or human expertise. To assess the effectiveness of our proposed model, we performed experiments on a dataset that covered a specific domain. We claim that our proposal is a suitable solution for scalable and versatile knowledge graph construction and may be applied to different and novel contexts.