Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fathallah, Nadeen, Staab, Steffen, Algergawy, Alsayed
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.02035
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913595331182592
author Fathallah, Nadeen
Staab, Steffen
Algergawy, Alsayed
author_facet Fathallah, Nadeen
Staab, Steffen
Algergawy, Alsayed
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02035
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLMs4Life: Large Language Models for Ontology Learning in Life Sciences
Fathallah, Nadeen
Staab, Steffen
Algergawy, Alsayed
Artificial Intelligence
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.
title LLMs4Life: Large Language Models for Ontology Learning in Life Sciences
topic Artificial Intelligence
url https://arxiv.org/abs/2412.02035