A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models

arXiv:2402.10779v1 Announce Type: new
Abstract: Zero-shot link prediction (ZSLP) on knowledge graphs aims at automatically identifying relations between given entities. Existing methods primarily employ auxiliary information to predict tail entity given head entity and its relation, yet face challenges due to the occasional unavailability of such detailed information and the inherent simplicity of predicting tail entities based on semantic similarities. Even though Large Language Models (LLMs) offer a promising solution to predict unobserved relations between the head and tail entity …

abstract arxiv challenges cs.cl face framework graph graphs head information knowledge knowledge graphs language language models large language large language models link prediction prediction relations transition type zero-shot