Prompt-Time Ontology-Driven Symbolic Knowledge Capture with Large Language Models
This addresses the need for personalization in applications like assistants, but it is incremental as it builds on existing ontology and knowledge-graph methods.
The paper tackles the problem of LLMs lacking the ability to learn personal information from user interactions by using an ontology-driven approach to capture such knowledge from prompts, and it evaluates this method with a custom dataset, making code and data publicly available.
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