Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Models

TL;DR

This paper introduces a method for capturing personal user information in large language models using ontology and knowledge-graph techniques, enabling models to better incorporate user preferences.

Contribution

It presents a novel approach combining ontology-driven knowledge capture with LLMs, specifically using the KNOW ontology to enhance personalization capabilities.

Findings

Successful knowledge capture demonstrated on a custom dataset

Code and datasets are publicly available for reproducibility

Method improves LLMs' ability to incorporate personal information

Abstract

In applications such as personal assistants, large language models (LLMs) must consider the user's personal information and preferences. However, LLMs lack the inherent ability to learn from user interactions. This paper explores capturing personal information from user prompts using ontology and knowledge-graph approaches. We use a subset of the KNOW ontology, which models personal information, to train the language model on these concepts. We then evaluate the success of knowledge capture using a specially constructed dataset. Our code and datasets are publicly available at https://github.com/HaltiaAI/paper-PTODSKC