The Mercurial Top-Level Ontology of Large Language Models

TL;DR

This paper analyzes the implicit ontological commitments in large language models like ChatGPT 3.5, proposing a systematic top-level ontology to understand their underlying assumptions and categorizations in generated texts.

Contribution

It introduces a novel approach to uncover and formalize the implicit ontological commitments of LLMs, including a taxonomy and an OWL ontology file.

Findings

GPT's top-level ontology resembles existing ontologies

Challenges include ontological overload and ambiguity in LLM texts

Systematized account aids understanding of LLM's implicit assumptions

Abstract

In our work, we systematize and analyze implicit ontological commitments in the responses generated by large language models (LLMs), focusing on ChatGPT 3.5 as a case study. We investigate how LLMs, despite having no explicit ontology, exhibit implicit ontological categorizations that are reflected in the texts they generate. The paper proposes an approach to understanding the ontological commitments of LLMs by defining ontology as a theory that provides a systematic account of the ontological commitments of some text. We investigate the ontological assumptions of ChatGPT and present a systematized account, i.e., GPT's top-level ontology. This includes a taxonomy, which is available as an OWL file, as well as a discussion about ontological assumptions (e.g., about its mereology or presentism). We show that in some aspects GPT's top-level ontology is quite similar to existing top-level ontologies. However, there are significant challenges arising from the flexible nature of LLM-generated texts, including ontological overload, ambiguity, and inconsistency.