KGValidator: A Framework for Automatic Validation of Knowledge Graph Construction

arXiv:2404.15923v1 Announce Type: cross
Abstract: This study explores the use of Large Language Models (LLMs) for automatic evaluation of knowledge graph (KG) completion models. Historically, validating information in KGs has been a challenging task, requiring large-scale human annotation at prohibitive cost. With the emergence of general-purpose generative AI and LLMs, it is now plausible that human-in-the-loop validation could be replaced by a generative agent. We introduce a framework for consistency and validation when using generative models to validate knowledge graphs. …

abstract annotation arxiv construction cost cs.ai cs.cl emergence evaluation framework general generative graph human information knowledge knowledge graph language language models large language large language models llms scale study type validation