Infusing Knowledge into Large Language Models with Contextual Prompts

arXiv:2403.01481v1 Announce Type: new
Abstract: Knowledge infusion is a promising method for enhancing Large Language Models for domain-specific NLP tasks rather than pre-training models over large data from scratch. These augmented LLMs typically depend on additional pre-training or knowledge prompts from an existing knowledge graph, which is impractical in many applications. In contrast, knowledge infusion directly from relevant documents is more generalisable and alleviates the need for structured knowledge graphs while also being useful for entities that are usually not …

abstract applications arxiv augmented llms cs.cl data domain graph knowledge knowledge graph language language models large language large language models llms nlp pre-training prompts scratch tasks training training models type