Prompt-Time Symbolic Knowledge Capture with Large Language Models
This work addresses a bottleneck for personal AI assistants by providing incremental improvements in knowledge capture mechanisms.
The paper tackles the problem of enabling prompt-driven knowledge capture in large language models, particularly for knowledge graphs, by exploring zero-shot, few-shot, and fine-tuning methods for prompt-to-triple generation, with results assessed on a synthetic dataset.
Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper investigates utilizing the existing LLM capabilities to enable prompt-driven knowledge capture, with a particular emphasis on knowledge graphs. We address this challenge by focusing on prompt-to-triple (P2T) generation. We explore three methods: zero-shot prompting, few-shot prompting, and fine-tuning, and then assess their performance via a specialized synthetic dataset. Our code and datasets are publicly available at https://github.com/HaltiaAI/paper-PTSKC.