Contextualization Distillation from Large Language Model for Knowledge Graph Completion

TL;DR

This paper presents Contextualization Distillation, a method that enhances knowledge graph completion by transforming triplets into context-rich segments using large language models, improving model performance and explainability.

Contribution

The paper introduces a novel distillation approach that leverages LLMs to generate contextual triplets and auxiliary tasks, boosting KGC performance across various models and datasets.

Findings

Consistent performance improvements across multiple datasets.

Enhanced explainability and insight into path selection.

Effective integration with both discriminative and generative KGC models.

Abstract

While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing corpora collected from Wikipedia articles or synsets definitions often limits the potential of PLM-based KGC models. To surmount these challenges, we introduce the Contextualization Distillation strategy, a versatile plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models (LLMs) to transform compact, structural triplets into context-rich segments. Subsequently, we introduce two tailored auxiliary tasks, reconstruction and contextualization, allowing smaller KGC models to assimilate insights from these enriched triplets. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach, revealing consistent performance enhancements irrespective of underlying pipelines or architectures. Moreover, our analysis makes our method more explainable and provides insight into generating path selection, as well as the choosing of suitable distillation tasks. All the code and data in this work will be released at https://github.com/David-Li0406/Contextulization-Distillation