知识提示学习综述

Knowledge-based prompting learning has become a research hotspot in NLP (Natural Language Processing) in recent years. By introducing external knowledge into prompts to provide background information, it effectively enhances the model\'s understanding and performance. Starting from the concept of prompting learning, this paper introduces common knowledge sources in knowledge prompts and the two main methods for generating knowledge prompts: knowledge base retrieval and model generation. Then, this article emphasizes the widespread application of knowledge prompting learning in many downstream tasks. Finally,the development trends of knowledge prompting learning is provided.