LLMs4Life: Large Language Models for Ontology Learning in Life Sciences

TL;DR

This paper enhances Large Language Models for ontology learning in life sciences by extending the NeOn-GPT pipeline with advanced prompt engineering and ontology reuse, demonstrating improved domain-specific reasoning and structural depth.

Contribution

It introduces an extended NeOn-GPT pipeline with novel prompt techniques and ontology reuse for better ontology learning in complex, specialized domains like life sciences.

Findings

LLMs can generate more comprehensive ontologies with hierarchical depth.

Enhanced prompt engineering improves domain-specific reasoning.

The approach scales effectively to complex life science ontologies.

Abstract

Ontology learning in complex domains, such as life sciences, poses significant challenges for current Large Language Models (LLMs). Existing LLMs struggle to generate ontologies with multiple hierarchical levels, rich interconnections, and comprehensive class coverage due to constraints on the number of tokens they can generate and inadequate domain adaptation. To address these issues, we extend the NeOn-GPT pipeline for ontology learning using LLMs with advanced prompt engineering techniques and ontology reuse to enhance the generated ontologies' domain-specific reasoning and structural depth. Our work evaluates the capabilities of LLMs in ontology learning in the context of highly specialized and complex domains such as life science domains. To assess the logical consistency, completeness, and scalability of the generated ontologies, we use the AquaDiva ontology developed and used in the collaborative research center AquaDiva as a case study. Our evaluation shows the viability of LLMs for ontology learning in specialized domains, providing solutions to longstanding limitations in model performance and scalability.