GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs

TL;DR

GenIC leverages large language models to improve knowledge graph instance completion by combining property prediction and link prediction, utilizing textual descriptions and schema patterns for enhanced fact inference.

Contribution

This paper introduces GenIC, an end-to-end LLM-based framework that combines classification and generative tasks for more accurate knowledge graph instance completion.

Findings

Outperforms existing baselines on three datasets.

Effectively uses textual descriptions and schema patterns.

Demonstrates the benefit of a two-step generative approach.

Abstract

Knowledge graph completion aims to address the gaps of knowledge bases by adding new triples that represent facts. The complexity of this task depends on how many parts of a triple are already known. Instance completion involves predicting the relation-tail pair when only the head is given (h, ?, ?). Notably, modern knowledge bases often contain entity descriptions and types, which can provide valuable context for inferring missing facts. By leveraging these textual descriptions and the ability of large language models to extract facts from them and recognize patterns within the knowledge graph schema, we propose an LLM-powered, end-to-end instance completion approach. Specifically, we introduce GenIC: a two-step Generative Instance Completion framework. The first step focuses on property prediction, treated as a multi-label classification task. The second step is link prediction, framed as a generative sequence-to-sequence task. Experimental results on three datasets show that our method outperforms existing baselines. Our code is available at https://github.com/amal-gader/genic.