This volume presents the proceedings of the Special Sessions on “Harmonising Generative AI and Semantic Web Technologies: Opportunities, Challenges, and Benchmarks”, held on November 13, 2024, as part of the International Semantic Web Conference (ISWC) 2024. ISWC is a leading venue for research on the Semantic Web, knowledge graphs, and web data. The Special Sessions were introduced this year to facilitate focused discussions, encourage participation, and build community around emerging topics. This year's focus was the intersection of Generative AI and Semantic Web technologies, addressing their synergies, limitations, and future directions. The sessions aimed to advance research in this area by fostering discussions and collaborative problemsolving among researchers, practitioners, and industry leaders. A key focus was the integration of Large Language Models (LLMs) into knowledge engineering pipelines supporting the lifecycle of ontologies and knowledge graphs (KGs). This integration presents new opportunities for knowledge representation, reasoning, and data interoperability. The sessions were structured around three key themes, explored in a 90-minute slot. Each theme addresses a critical aspect of harmonizing Generative AI and Semantic Web technologies. The three themes for this year were: 1. Benchmarking & Reproducibility in Generative AI for Knowledge Engineering: This theme focused on the crucial need for robust evaluation methods and standardised benchmarks to assess the performance of LLMs in knowledge engineering tasks. The presentations and discussions in this slot highlighted the challenges of evaluating tasks like ontology construction, validation, and population, and explored the development of suitable datasets and metrics.
Each slot adopted an interactive format designed to foster collaboration and knowledge sharing. The slot started with concise presentations of selected short papers, setting the stage for focused discussions and working group activities. These discussions provided a platform for participants to delve deeper into the presented research, identify open challenges, and brainstorm potential solutions. The follow-up segments encouraged participants to form working groups, which would continue collaborating beyond the session to develop concrete outputs, such as white papers and research agendas.
Topics discussed by the working groups included: defining benchmarks for knowledge engineering pipelines, using LLMs for distributed knowledge graph and ontology alignment, leveraging LLMs for educational applications, ensuring explainability in AI-generated results, defining knowledge contexts, and integrating LLMs with semantic layers in common APIs.
These proceedings contain the kickstarter papers submitted to the Special Sessions, reflecting the authors’ diverse perspectives and research interests. Participants were encouraged to continue their collaborations beyond the session and contribute to a white paper summarizing key findings, open problems, and research directions.
The Special Sessions were well attended, demonstrating strong interest in the convergence of Generative AI and Semantic Web technologies. They proved to be an efective platform for fostering collaboration and advancing research in this interdisciplinary domain.
We hope the ideas presented in this volume will contribute to future research and innovation at the intersection of Generative AI and the Semantic Web.
We are grateful to Aidan Hogan and the ISWC 2024 conference for their support in establishing this new forum for discussing and advancing research on these emerging topics.
Reham Alharbi, University of Liverpool Jacopo de Berardinis, University of Liverpool Paul Groth, University of Amsterdam Albert Meroño-Peñuela, King’s College London Elena Simperl, King’s College London Valentina Tamma, University of Liverpool