Leveraging Ontologies in Standard Language Models for Research Capabilities: An Evaluation of Performance

Abstract
The emergence of Standard Language Models (SLMs) augmented with ontologies has led to remarkable real-world understanding and enabled the applications in knowledge reasoning and knowledge discovery, revolutionizing AI research capabilities across various fi elds including science and humanities. This paper explores the utilization of various ontologies to enrich SLMs and their performance in generating research questions, designing experiments, and making novel discoveries based on research data across multiple disciplines. We analyze the performance of diff erent ontologies in enriching SLMs with a particular focus on their impact on real-world understanding and their role in AI-driven research advancements. This study serves as a useful resource for researchers seeking to enhance real-world understanding in SLMs as well as those who uses SLMs to maximize their research across disciplines.

Disclaimer: This paper is a work of fi ction, written in 2023 and describing research that may be carried out in 2043. For this reason, it includes citations to papers produced in the period 2024-2043, which have not been published (yet); all citations prior to 2024 refer instead to papers already in the literature. Any reference or resemblance to actual events or people or businesses, past present or future, is entirely coincidental and the product of the author’s imagination.