Workshop on LLM-driven Knowledge Graph and Ontology Engineering (llms4kgoe) 2026

First Workshop | Co-located with ESWC 2026 (23rd European Semantic Web Conference)

About

The maturing of Semantic Web technologies cannot be separated from the need for high-quality, reusable ontologies. However, traditional ontology engineering is a notoriously difficult, time-consuming, and expert-driven process. The advent of LLMs presents a paradigm shift, promising to accelerate and democratize this process, enabling "specialists from beyond computer science" to develop their own models.

While the potential is enormous, automated ontology creation from LLMs presents significant challenges that the Semantic Web and knowledge engineering communities have yet to systematically address. If the foundational ontologies generated by LLMs are of poor quality, incoherent, or formally incorrect, the downstream AI systems built upon them will inherit these critical flaws.

This workshop focuses on the emerging and rapidly evolving intersection of Large Language Models (LLMs), semantic technologies, and ontology engineering. It addresses the challenges and opportunities associated with leveraging LLMs for ontology creation, refinement, and validation. The workshop encompasses both theoretical and practical aspects of LLM-based ontology construction, including semi-automated/fully automated ontology generation pipelines, evaluation methodologies, and strategies for reducing hallucinations.

Motivation: This workshop is motivated by three key observations: (1) the growing practical deployment of LLMs in knowledge graph and ontology construction projects with minimal formal evaluation frameworks; (2) the lack of systematic comparison between LLM-based and traditional ontology engineering approaches; and (3) the absence of community consensus on appropriate evaluation methodologies and quality metrics specific to LLM-generated ontologies.

Topics of Interest

We welcome contributions on topics concerning the development and assessment of high-quality ontologies, both manually engineered and automatically generated using large language models (LLMs). The main topics of interest include, but are not limited to, the following:

Workshop Format

Type: First Workshop
Length: Full Day (6-7 hours including breaks)
Mode: In-person (aligned with conference on-site infrastructure)

We plan the workshop to begin with an invited talk followed by presentations of contributed papers (with discussion), and eventually, by an interactive session of breakout groups working on and discussing ontology design issues and patterns. We will conclude with joint reporting and a community town hall.

Submission Instructions

The papers will be (single-blind) peer-reviewed. The workshop proceedings will be published by CEUR, and manuscript must follow the CEUR-WS template. We will also provide the option of not archiving the submissions on CEUR to the authors.

Manuscripts will be submitted through EasyChair . For all manuscript submissions, at least one author must agree to review another paper

Paper Length:
Short papers: 5–9 pages (including references).
Regular papers: at least 10 pages (including references).

Presentation Requirement: At least one author of each accepted paper must register for the workshop and present the paper in person.

Important Dates

Programme

The workshop runs as a full-day event on May 11, 2026. All times are local to the conference venue.

Session 1: Opening and Keynote 09:00 – 10:30

  • 09:00 – 09:45 Keynote 45 min — chair welcomes attendees in the intro
  • 09:45 – 10:07 Paper 1 Ground-truth Construction and Evaluation of LLM Contribution to Life Sciences Tool Annotation Ulysse Le Clanche et al. 15 min presentation + 7 min Q&A
  • 10:07 – 10:30 Paper 2 Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field Tanay Aggarwal et al. 15 min presentation + 8 min Q&A
  • 10:30 – 11:00 Coffee Break

Session 2: Four Papers 11:00 – 12:20

  • 11:00 – 11:20 Paper 3 Automating AI Risk Profiling with LLM-Engineered OWL 2 Axioms Manas Goyal et al. 15 min presentation + 5 min Q&A
  • 11:20 – 11:40 Paper 4 Pitfalls in AI-Generated Ontologies: Strategies for Detection and Mitigation Pasquale Lisena et al. 15 min presentation + 5 min Q&A
  • 11:40 – 12:00 Paper 5 PERSEUS: PERceptual Semantic Extraction & Unified System Aryan Singh Dalal and Hande McGinty 15 min presentation + 5 min Q&A
  • 12:00 – 12:20 Paper 6 OG-NSD: Neuro-Symbolic Ontology Drafting from Natural-Language Requirements Efstratios Skaperdas et al. 15 min presentation + 5 min Q&A
  • 12:20 – 14:00 Lunch Break

Session 3: Three Papers and Closing 14:00 – 15:30

  • 14:00 – 14:22 Paper 7 MASEO: A Multi-Agent System for Explainable Ontology Generation Jiayi Li et al. 15 min presentation + 7 min Q&A
  • 14:22 – 14:45 Paper 8 IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering Elliott Watkiss-Leek et al. 15 min presentation + 8 min Q&A
  • 14:45 – 15:07 Paper 9 Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach Abid Talukder et al. 15 min presentation + 7 min Q&A
  • 15:07 – 15:30 Closing discussion and wrap-up
  • 15:30 Workshop ends at the afternoon coffee break

Organization

General Chairs

Program Committee