LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs

arXiv:2402.11804v1 Announce Type: cross
Abstract: Knowledge Graph (KG) inductive reasoning, which aims to infer missing facts from new KGs that are not seen during training, has been widely adopted in various applications. One critical challenge of KG inductive reasoning is handling low-resource scenarios with scarcity in both textual and structural aspects. In this paper, we attempt to address this challenge with Large Language Models (LLMs). Particularly, we utilize the state-of-the-art LLMs to generate a graph-structural prompt to enhance the pre-trained …

abstract applications arxiv challenge cs.ai cs.cl cs.si facts graph graphs inductive knowledge knowledge graph knowledge graphs llm low reasoning textual training type