Knowledge Graph Large Language Model (KG-LLM) for Link Prediction

arXiv:2403.07311v1 Announce Type: cross
Abstract: The task of predicting multiple links within knowledge graphs (KGs) stands as a challenge in the field of knowledge graph analysis, a challenge increasingly resolvable due to advancements in natural language processing (NLP) and KG embedding techniques. This paper introduces a novel methodology, the Knowledge Graph Large Language Model Framework (KG-LLM), which leverages pivotal NLP paradigms, including chain-of-thought (CoT) prompting and in-context learning (ICL), to enhance multi-hop link prediction in KGs. By converting the KG …

abstract analysis arxiv challenge cs.cl cs.lg embedding graph graphs knowledge knowledge graph knowledge graphs language language model language processing large language large language model link prediction llm methodology multiple natural natural language natural language processing nlp novel paper prediction processing type