Skip to main content Skip to main navigation

Publication

Modular Design Patterns for Generative Neuro-Symbolic Systems

Maaike H. T. de Boer; Quirine S. Smit; Michael van Bekkum; André Meyer-Vitali; Thomas Schmid
In: Ludwig-Maximilians-Universität München Bruno Sartini; LISN Joe Raad; EURECOM Pasquale Lisena; King’s College London Albert Meroño Peñuela; Institute for Artificial Intelligence Michael Beetz; Vrije Universiteit Amsterdam Inès Blin; Cluster of Excellence Cognitive Interaction Technology (CITEC) Philipp Cimiano; University of Manchester Jacopo de Berardinis; L3S Research Center Simon Gottschalk; Vrije Universiteit Amsterdam Filip Ilievski; King’s College London Nitisha Jain; King’s College London Jongmo Kim; Institute for Artificial Intelligence Michaela Kümpel; Knowledge Media Institute Enrico Motta; Vrije Universiteit Amsterdam Ilaria Tiddi; Cluster of Excellence Cognitive Interaction Technology (CITEC) Jan-Philipp Töberg (Hrsg.). Joint Proceedings of the ESWC 2024 Workshops and Tutorials. European Semantic Web Conference (ESWC-2024), GeNeSy, located at 21th European Semantic Web Conference, May 26-27, Hersonissos, Greece, CEUR Workshop Proceedings, 5/2024.

Abstract

Developing systems that are able to generate novel outputs is one of the dominating trends in current Artificial Intelligence (AI) research. Both capabilities and availability of such generative systems, in particular of so-called Large Language Models (LLMs), have been exploding in recent years. While Neuro-Symbolic generative models offer advantages over purely statistical generative models, it is currently difficult to compare the different ways in which the training, fine-tuning and usage of the growing variety of such approaches is carried out. In this work, we use the modular design patterns and Boxology language of van Bekkum et al for this purpose and extend those to enable the representation of generative models, specifically LLMs. These patterns provide a general language to describe, compare and understand the different architectures and methods used. Our main aim is to support better understanding of generative models as well as to support engineering of LLM-based systems. In order to demonstrate the usefulness of this approach, we explore generative Neuro-Symbolic architectures and approaches as use cases for these generative design patterns.

Projects

More links