Knowledge graphs and ontologies provide structured, semantically rich frameworks that organize information into human-meaningful relationships, which support logic-based reasoning and decision-making. Neurosymbolic AI builds on these foundations by combining the strengths of symbolic approaches – such as formal reasoning and explainability – with the adaptability and scalability of (deep) neural systems and techniques. Together, they address longstanding challenges in AI, including generalization, robustness, and interpretability, offering solutions that are both data-driven and grounded in human-like reasoning.

Conversely, neural systems and techniques (including generative models such as LLMs) can be used to produce knowledge graphs and ontologies of various quality, for example through the extraction of knowledge from textual data.

The Knowledge Graphs, Ontologies and Neurosymbolic AI Special Track at the 19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025) aims to bring together researchers working at the broad intersection of (symbolic) knowledge representation and reasoning and with neural-based systems and techniques. We invite submissions that explore how neurosymbolic principles can enhance – or be enhanced by – knowledge graphs and ontologies.

Our goal is to foster the development of systems that do more than just “scale up” — they leverage structured knowledge, reasoning capabilities, and integrated symbolic components for creativity, interpretability, and trustworthiness.

Topics of Interest

Submissions are encouraged from all areas related neurosymbolic principles which enhance – or are enhanced by – knowledge graphs and ontologies. Relevant topics include, but are not limited to:

  • Ontology Embeddings
  • Ontology Engineering with Large Language Models
    • Using Prompts to Engineer Ontologies
    • Using Ontologies to Engineer Prompts
  • Symbolic Post-Processing with Neural Systems
  • Neural Systems for Ontology Matching
  • Ontology Alignment with Neural Systems
  • Reasoning with Neural Systems
  • Knowledge Graph Development & Engineering Methodologies with Neural Systems
  • Knowledge Graph Embeddings
  • KG and Ontologies in Retrieval Augmentation Systems

Notes

Please note that this is not a resources track. Papers that only present a framework or pipeline are not in-scope. Such engineering is valuable, of course, but should be presented in the context of its evaluation; correctness or other metrics; and production of reasonable KRR artifacts or their use thereof.

Contact

For inquiries related to this special track, please contact the track chairs: Cogan Shimizu (cogan.shimizu@wright.edu) and Claudia d’Amato (claudia.damato@uniba.it).

Submission

Please submit your paper according to the submission guidelines. In the submission form on OpenReview, please select the “Knowledge Graphs, Ontologies and Neurosymbolic AI” special track.