Harmonising Generative AI and Semantic Web Technologies at ISWC 2024
Date: November 13, 2024
Context
This special session aims to catalyse progress in Generative AI and Semantic Web Technologies by fostering in-depth discussions and collaborative problem-solving among researchers, practitioners, and industry leaders. The session will feature three dedicated slots, each focusing on a specific challenge or theme within the broader topic area. Through a combination of short paper presentations, focused discussions, and working groups, participants will share insights, identify open problems, and initiate collaborative projects. We encourage participation from researchers at all career stages.
The session is organised in three slots, each addressing a specific research agenda:
- Slot 1: Benchmarking & Reproducibility in Gen AI for Knowledge Engineering
- Slot 2: Bridging the Gap: Building Knowledge-Enhanced Gen AI
- Slot 3: Spotlight on Applications and Success Stories in Gen AI + Semantic Web
Each of the three slots will follow a similar structure designed to maximise engagement and facilitate tangible outcomes. This will include a combination of the following activities (please note that timings are purely indicative).
- Slot kickstarter: short paper overview (15 minutes): A selection of short papers, submitted in advance, will be briefly pitched by the panellist to provide a concise overview of relevant research, tools, or datasets, that will kickstart the discussion.
- Focused discussion (60 minutes): Moderated discussions will delve deeper into the presented topics, allowing participants to share perspectives, raise questions, and identify key challenges. Depending on the slot, these may include hands-on activities, brainstorming sessions, or collaborative exercises.
- Follow-up (15 minutes): The idea of follow-up is for members to form and coordinate groups (with a leader) that meet up later in the conference (at coffee, lunch, dinner, etc.) and follow up on concrete actions. This is expected to generate concrete outputs, such as white papers, research agendas, or project proposals.
Event Goals
We anticipate the following outcomes from the special session:
- White Papers: Each slot will lay the groundwork for a collaboratively authored white paper summarising key findings, open problems, and potential research directions. We anticipate publishing the white papers as part of a special issue in a journal (to be defined).
- Research Agendas: The discussions and workshops are expected to generate research agendas outlining priority areas for future investigation.
- Collaborative projects and open repositories: We hope the session will spark new collaborations and initiatives to address the identified challenges.
Schedule
11:00 – 11:05
Scene Setting
Slot 1
11:15 – 11:30
Slot 1 kickstarter presentations
Benchmarking – GenAI and Knowledge Engineering
Characteristics and Desiderata for Competency Question Benchmarks by Reham Alharbi, Jacopo de Berardinis, Floriana Grasso, Terry Payne and Valentina Tamma
Ontology Corpora for LLM-based Knowledge Engineering Research by Guntur Budi Herwanto, Stefani Tsaneva and Marta Sabou
LLMs for Ontology Engineering: A landscape of Tasks and Benchmarking challenges by Daniel Garijo, María Poveda-Villalón, Elvira Amador-Dominguez, Ziyuan Wang, Raul García-Castro and Oscar Corcho
Benchmarking Ontology Validation Capabilities of LLMs by Stefani Tsaneva, Guntur Budi Herwanto and Marta Sabou
Benchmarking LLM-based Ontology Conceptualization: A proposal by
Youssra Rebboud, Pasquale Lisena, Lionel Tailhardat and Raphael Troncy
11:30 – 12:35
Focused Discussion
Follow-up
12:30 – 14:00
Lunch break
Slot 2:
14:00 – 14:15
Slot 2 kickstarter presentations
Knowledge Enhanced GenAI – Using GenAI
LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs by Vincent Emonet, Jerven Bolleman, Severine Duvaud, Tarcisio Mendes de Farias and Ana Claudia Sima
A Benchmark for the Detection of Metalinguistic Disagreements between LLMs and Knowledge Graphs by Bradley Allen and Paul Groth
OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching by Zhangcheng Qiang, Kerry Taylor, Teresa Wang and Jing Jiang
A Comprehensive Benchmark for Evaluating LLM-Generated Ontologies by Julien Plu, Oscar Moreno Escobar, Edouard Trouillez, AxelleGapin and Raphaël Troncy
Explainable LLM-powered RAG To Tackle Tasks In The Unstructured-structured Data Spectrum by Dario Garigliotti
14:15 – 15:15
Focused Discussion
15:15 – 15:30
Follow-up
15:30 – 16:00
Coffee Break
Slot 3:
16:00 – 16:15
Slot 3 kickstarter presentations
Applications
Lessons Learned from Enterprise Question Answering on SQL Databases using LLMs and Knowledge Graphs by Juan F. Sequeda, Dean Allemang and Bryon Jacob
Assessing Large Language Models for SPARQL Query Generation in Scientific Question Answering by Antonello Meloni, Diego Reforgiato, Francesco Osborne, Angelo Salatino, Enrico Motta, Sahar Vahdati and Jens Lehmann
Information for Conversation Generation: Proposals Utilising Knowledge Graphs by Alex Clay and Ernesto Jiménez-Ruiz
Hybrid Evaluation of Socratic Questioning for Teaching by Eleni Ilkou, Stephan Linzbach and Jonas Wallat
ARCLIGHT: Automated Clustering and Curriculum Learning Guided by Human Training by Jamie McCusker, Henrique Santos, Rishi Singh, Sabbir Rashid, Abraham Sanders, Grace Roessling, Hongji Guo, Bashirul Biswas, Deborah L. McGuinness, Tomek Strzalkowski, Qiang Ji and Jay Miller
16:15 – 17:15
Focused Discussion
17:15 – 17:30
Follow-up
Organizers
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