Infusing Knowledge into Large Language Models with Contextual Prompts
This addresses the impracticality of knowledge graphs for domain-specific applications, though it appears incremental as it builds on existing knowledge infusion methods.
The paper tackles the problem of enhancing Large Language Models for domain-specific NLP tasks by proposing a knowledge infusion approach that generates prompts directly from input text context, eliminating the need for structured knowledge graphs. The method shows effectiveness in experiments evaluated through probing fine-tuned LLMs.
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 found in any knowledge graph. With this motivation, we propose a simple yet generalisable approach for knowledge infusion by generating prompts from the context in the input text. Our experiments show the effectiveness of our approach which we evaluate by probing the fine-tuned LLMs.