Ontologies are known to improve the accuracy of Large Language Models (LLMs) when translating natural language queries into a formal query language like SQL or SPARQL. There are two ways to leverage ontologies when working with LLMs. One is to fine-tune the model, i.e., to enhance it with specific domain knowledge. Another is the zero-shot prompting approach, where the ontology is provided as part of the input question. Unfortunately, modern enterprises typically have ontologies that are too large to fit in a prompt due to LLM's token size limitations. We present a solution that incrementally reveals "just enough" of an ontology that is needed to answer a given question.
@article{arxiv.2410.09244,
title = {Using off-the-shelf LLMs to query enterprise data by progressively revealing ontologies},
author = {C. Civili and E. Sherkhonov and R. E. K. Stirewalt},
journal= {arXiv preprint arXiv:2410.09244},
year = {2024}
}