My Ontologist: Evaluating BFO-Based AI for Definition Support

Generative artificial intelligence (AI), exemplified by the release of GPT-3.5 in 2022, has significantly advanced the potential applications of large language models (LLMs), including in the realms of ontology development and knowledge graph creation. Ontologies, which are structured frameworks for...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Benson, Carter, Sculley, Alec, Liebers, Austin, Beverley, John
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Benson, Carter
Sculley, Alec
Liebers, Austin
Beverley, John
description Generative artificial intelligence (AI), exemplified by the release of GPT-3.5 in 2022, has significantly advanced the potential applications of large language models (LLMs), including in the realms of ontology development and knowledge graph creation. Ontologies, which are structured frameworks for organizing information, and knowledge graphs, which combine ontologies with actual data, are essential for enabling interoperability and automated reasoning. However, current research has largely overlooked the generation of ontologies extending from established upper-level frameworks like the Basic Formal Ontology (BFO), risking the creation of non-integrable ontology silos. This study explores the extent to which LLMs, particularly GPT-4, can support ontologists trained in BFO. Through iterative development of a specialized GPT model named "My Ontologist," we aimed to generate BFO-conformant ontologies. Initial versions faced challenges in maintaining definition conventions and leveraging foundational texts effectively. My Ontologist 3.0 showed promise by adhering to structured rules and modular ontology suites, yet the release of GPT-4o disrupted this progress by altering the model's behavior. Our findings underscore the importance of aligning LLM-generated ontologies with top-level standards and highlight the complexities of integrating evolving AI capabilities in ontology engineering.
doi_str_mv 10.48550/arxiv.2407.17657
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_17657</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_17657</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_176573</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zM0NzM152Sw9a1U8M8ryc_JT88sLrFScC1LzClNLMnMS1dwcvPXdUosTk1RcPRUSMsvUnBJTcvMyyzJzM9TCC4tKMgvKuFhYE1LzClO5YXS3Azybq4hzh66YIviC4oycxOLKuNBFsaDLTQmrAIA0kc0wg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>My Ontologist: Evaluating BFO-Based AI for Definition Support</title><source>arXiv.org</source><creator>Benson, Carter ; Sculley, Alec ; Liebers, Austin ; Beverley, John</creator><creatorcontrib>Benson, Carter ; Sculley, Alec ; Liebers, Austin ; Beverley, John</creatorcontrib><description>Generative artificial intelligence (AI), exemplified by the release of GPT-3.5 in 2022, has significantly advanced the potential applications of large language models (LLMs), including in the realms of ontology development and knowledge graph creation. Ontologies, which are structured frameworks for organizing information, and knowledge graphs, which combine ontologies with actual data, are essential for enabling interoperability and automated reasoning. However, current research has largely overlooked the generation of ontologies extending from established upper-level frameworks like the Basic Formal Ontology (BFO), risking the creation of non-integrable ontology silos. This study explores the extent to which LLMs, particularly GPT-4, can support ontologists trained in BFO. Through iterative development of a specialized GPT model named "My Ontologist," we aimed to generate BFO-conformant ontologies. Initial versions faced challenges in maintaining definition conventions and leveraging foundational texts effectively. My Ontologist 3.0 showed promise by adhering to structured rules and modular ontology suites, yet the release of GPT-4o disrupted this progress by altering the model's behavior. Our findings underscore the importance of aligning LLM-generated ontologies with top-level standards and highlight the complexities of integrating evolving AI capabilities in ontology engineering.</description><identifier>DOI: 10.48550/arxiv.2407.17657</identifier><language>eng</language><subject>Computer Science - Databases</subject><creationdate>2024-07</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.17657$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.17657$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Benson, Carter</creatorcontrib><creatorcontrib>Sculley, Alec</creatorcontrib><creatorcontrib>Liebers, Austin</creatorcontrib><creatorcontrib>Beverley, John</creatorcontrib><title>My Ontologist: Evaluating BFO-Based AI for Definition Support</title><description>Generative artificial intelligence (AI), exemplified by the release of GPT-3.5 in 2022, has significantly advanced the potential applications of large language models (LLMs), including in the realms of ontology development and knowledge graph creation. Ontologies, which are structured frameworks for organizing information, and knowledge graphs, which combine ontologies with actual data, are essential for enabling interoperability and automated reasoning. However, current research has largely overlooked the generation of ontologies extending from established upper-level frameworks like the Basic Formal Ontology (BFO), risking the creation of non-integrable ontology silos. This study explores the extent to which LLMs, particularly GPT-4, can support ontologists trained in BFO. Through iterative development of a specialized GPT model named "My Ontologist," we aimed to generate BFO-conformant ontologies. Initial versions faced challenges in maintaining definition conventions and leveraging foundational texts effectively. My Ontologist 3.0 showed promise by adhering to structured rules and modular ontology suites, yet the release of GPT-4o disrupted this progress by altering the model's behavior. Our findings underscore the importance of aligning LLM-generated ontologies with top-level standards and highlight the complexities of integrating evolving AI capabilities in ontology engineering.</description><subject>Computer Science - Databases</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zM0NzM152Sw9a1U8M8ryc_JT88sLrFScC1LzClNLMnMS1dwcvPXdUosTk1RcPRUSMsvUnBJTcvMyyzJzM9TCC4tKMgvKuFhYE1LzClO5YXS3Azybq4hzh66YIviC4oycxOLKuNBFsaDLTQmrAIA0kc0wg</recordid><startdate>20240724</startdate><enddate>20240724</enddate><creator>Benson, Carter</creator><creator>Sculley, Alec</creator><creator>Liebers, Austin</creator><creator>Beverley, John</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240724</creationdate><title>My Ontologist: Evaluating BFO-Based AI for Definition Support</title><author>Benson, Carter ; Sculley, Alec ; Liebers, Austin ; Beverley, John</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_176573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Benson, Carter</creatorcontrib><creatorcontrib>Sculley, Alec</creatorcontrib><creatorcontrib>Liebers, Austin</creatorcontrib><creatorcontrib>Beverley, John</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Benson, Carter</au><au>Sculley, Alec</au><au>Liebers, Austin</au><au>Beverley, John</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>My Ontologist: Evaluating BFO-Based AI for Definition Support</atitle><date>2024-07-24</date><risdate>2024</risdate><abstract>Generative artificial intelligence (AI), exemplified by the release of GPT-3.5 in 2022, has significantly advanced the potential applications of large language models (LLMs), including in the realms of ontology development and knowledge graph creation. Ontologies, which are structured frameworks for organizing information, and knowledge graphs, which combine ontologies with actual data, are essential for enabling interoperability and automated reasoning. However, current research has largely overlooked the generation of ontologies extending from established upper-level frameworks like the Basic Formal Ontology (BFO), risking the creation of non-integrable ontology silos. This study explores the extent to which LLMs, particularly GPT-4, can support ontologists trained in BFO. Through iterative development of a specialized GPT model named "My Ontologist," we aimed to generate BFO-conformant ontologies. Initial versions faced challenges in maintaining definition conventions and leveraging foundational texts effectively. My Ontologist 3.0 showed promise by adhering to structured rules and modular ontology suites, yet the release of GPT-4o disrupted this progress by altering the model's behavior. Our findings underscore the importance of aligning LLM-generated ontologies with top-level standards and highlight the complexities of integrating evolving AI capabilities in ontology engineering.</abstract><doi>10.48550/arxiv.2407.17657</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.17657
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_17657
source arXiv.org
subjects Computer Science - Databases
title My Ontologist: Evaluating BFO-Based AI for Definition Support
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T08%3A00%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=My%20Ontologist:%20Evaluating%20BFO-Based%20AI%20for%20Definition%20Support&rft.au=Benson,%20Carter&rft.date=2024-07-24&rft_id=info:doi/10.48550/arxiv.2407.17657&rft_dat=%3Carxiv_GOX%3E2407_17657%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true