Making Large Language Models Perform Better in Knowledge Graph Completion

Anonymous

Abstract: Large language model (LLM) based knowledge graph completion (KGC) aims to predict the missing triples in the KGs with LLMs. However, research about LLM-based KGC fails to sufficiently harness LLMs' inference proficiencies, overlooking critical structural information integral to KGs. In this paper, we explore methods to incorporate structural information into the LLMs, with the overarching goal of facilitating structurally-aware reasoning. We propose a Knowledge Prefix Adapter (KoPA) to fulfill this stated goal. The KoPA uses a structural pre-training phase to comprehend the intricate relations and entities within KGs. Then KoPA communicates such structural understanding to the LLMs through a knowledge prefix adapter which projects the structural embeddings into the textual space and obtains virtual knowledge tokens positioned as a prefix of the input prompt. We conduct comprehensive experiments and provide incisive analysis concerning how the introduction of structural information would be better for LLM's knowledge reasoning ability. Our code and data are available at https://anonymous.4open.science/r/KoPA-0122.

Paper Type: long

Research Area: NLP Applications

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English