LMs4OL - Large Language Models for Ontology Learning
2025 edition
The 2nd Large Language Models for Ontology Learning Challenge is co-located with the 24th International Semantic Web Conference (ISWC 2025) in Nara, Japan at November 2–6, 2025
Challenge Overview
The 2nd LLMs4OL Challenge@ISWC 2025 invites researchers and practitioners to explore the capabilities of Large Language Models (LLMs) in automating Ontology Learning (OL). As the Semantic Web evolves, automating the extraction and structuring of knowledge becomes paramount. This challenge focuses on leveraging LLMs to enhance OL processes, contributing to more intelligent and interoperable web systems. Building upon the success of the 1st LLMs4OL Challenge at ISWC 2024, this second edition aims to further the community’s understanding and development of LLM-driven OL methodologies.
Challenge Tasks
Participants can engage in one or more of the following tasks:
- Task A - Text2Onto: Extract ontological terminologies and types from a raw text.
- Task B - Term Typing: Discover the generalized type for a lexical term.
- Task C - Taxonomy Discovery: Discover the taxonomic hierarchy between type pairs.
- Task D - Non-Taxonomic Relation Extraction: Identify non-taxonomic, semantic relations between types. Each task is designed to address specific aspects of OL, encouraging innovative approaches and solutions.
Find detailed information on the workshop page: https://sites.google.com/view/llms4ol2025
2024 edition
NFDI4DS partners organize Shared Tasks co-located with ISWC2024 in Baltimore, USA, 11-15 November, 2024.
The Semantic Web aims to enrich the current web with structured knowledge and metadata for enhanced interoperability and understanding across systems. Central to this endeavor is Ontology Learning (OL), which automates the extraction of this structured knowledge from unstructured data, crucial for building dynamic ontologies foundational to the Semantic Web. The advent of Large Language Models (LLMs) has introduced a promising approach to OL, leveraging their deep linguistic understanding and pattern inference capabilities to automate OL.
This challenge aims to align with the Semantic Web community’s goals of making the web more intelligent and user-friendly, offering a novel avenue for exploring the intersection of LLMs and OL. Participation in this challenge will contribute to evolving the Semantic Web, enabling more sophisticated services that utilize structured knowledge effectively.
Find detailed information on the workshop page: https://sites.google.com/view/llms4ol/
Find the official published proceedings: LLMs4OL 2024: The 1st Large Language Models for Ontology Learning Challenge at the 23rd ISWC.