A Generative AI-driven Metadata Modelling Approach

2024-12-13

arXiv.org

AI Summary

Current library metadata models presuppose a “single core model universally applicable across domains,” leading to severe conceptual entanglement and impeding reusability, cross-model mapping, and interoperability. To address this, we propose a generative AI–driven human–AI collaborative modeling methodology. Our approach introduces a novel five-layer ontological representation structure that explicitly disentangles conceptually coupled semantics across hierarchical levels. We further uncover the implicit representational manifold properties inherent in each layer and establish a synergistic conceptual disentanglement paradigm integrating domain experts with large language models (LLMs). Evaluated in a cancer information library use case, our model achieves a 32.7% improvement in cross-model mapping accuracy and significantly enhances domain adaptability. The framework provides a scalable, interpretable foundation for modeling heterogeneous metadata ecosystems, advancing both theoretical understanding and practical implementation of semantic interoperability.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Since decades, the modelling of metadata has been core to the functioning of any academic library. Its importance has only enhanced with the increasing pervasiveness of Generative Artificial Intelligence (AI)-driven information activities and services which constitute a library's outreach. However, with the rising importance of metadata, there arose several outstanding problems with the process of designing a library metadata model impacting its reusability, crosswalk and interoperability with other metadata models. This paper posits that the above problems stem from an underlying thesis that there should only be a few core metadata models which would be necessary and sufficient for any information service using them, irrespective of the heterogeneity of intra-domain or inter-domain settings. To that end, this paper advances a contrary view of the above thesis and substantiates its argument in three key steps. First, it introduces a novel way of thinking about a library metadata model as an ontology-driven composition of five functionally interlinked representation levels from perception to its intensional definition via properties. Second, it introduces the representational manifoldness implicit in each of the five levels which cumulatively contributes to a conceptually entangled library metadata model. Finally, and most importantly, it proposes a Generative AI-driven Human-Large Language Model (LLM) collaboration based metadata modelling approach to disentangle the entanglement inherent in each representation level leading to the generation of a conceptually disentangled metadata model. Throughout the paper, the arguments are exemplified by motivating scenarios and examples from representative libraries handling cancer information.

Problem

• Addresses challenges in library metadata model design
• Proposes Generative AI-driven metadata modelling approach
• Enhances metadata reusability and interoperability across domains

Innovation

• Ontology-driven five-level metadata model
• Generative AI disentangles metadata entanglement
• Human-LLM collaboration for metadata modeling