Making Large Language Models Perform Better in Knowledge Graph Completion

Yichi Zhang, Zhuo Chen, Lingbing Guo, yajing Xu, Wen Zhang, Huajun Chen

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 structure-aware reasoning. We first discuss on the existing LLM paradigms like in-context learning and instruction tuning, proposing basic structural information injection approaches. Then we propose a Kno}wledge Prefix Adapter (KoPA) to fulfill this stated goal. The KoPA uses a structural pre-training phase to comprehend the intricate entities and relations within KGs, representing them as structural embeddings. Then KoPA communicates such **cross-modal structural information 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 cross-modal structural information would be better for LLM's factual knowledge reasoning ability. Our code and data are available at https://anonymous.4open.science/r/KoPA-3415.

Primary Subject Area: [Generation] Multimedia Foundation Models

Secondary Subject Area: [Content] Media Interpretation, [Content] Multimodal Fusion

Relevance To Conference: This paper focus on large language model based structural knowledge reasoning, which is an important task in current LLM research. In this paper, we propose a cross-modal prefix adapter approach that attempts to allow large language models to understand features derived from knowledge graph structural information, which involves the comprehension task of cross-modal understanding between graph and texts, an important multimodal and multimedia learning focus. We believe that this paper also meets the submission requirements for the ACM MM conference.

Submission Number: 3415