English

Prompt-Time Symbolic Knowledge Capture with Large Language Models

Computation and Language 2024-02-02 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2402.00414,
  title  = {Prompt-Time Symbolic Knowledge Capture with Large Language Models},
  author = {Tolga Çöplü and Arto Bendiken and Andrii Skomorokhov and Eduard Bateiko and Stephen Cobb and Joshua J. Bouw},
  journal= {arXiv preprint arXiv:2402.00414},
  year   = {2024}
}

Comments

8 pages, 5 figures, 1 table preprint. Under review

R2 v1 2026-06-28T14:34:13.823Z