# A Generative AI-driven Metadata Modelling Approach

arXiv: https://arxiv.org/abs/2501.04008 · HTML: https://mlsanity.com/paper/2501.04008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 98 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [The role of metadata in reproducible computational research](https://mlsanity.com/paper/2006.08589/) (2020)
- [The Landscape of Ontology Reuse Approaches](https://mlsanity.com/paper/2011.12599/) (2020)
- [A Diversity-Aware Domain Development Methodology](https://mlsanity.com/paper/2208.13064/) (2022)
- [Smart Cities, Smart Libraries and Smart Knowledge Managers: Ushering in the neo-Knowledge Society](https://mlsanity.com/paper/2202.08118/) (2022)
- [Disentangling Domain Ontologies](https://mlsanity.com/paper/2304.00004/) (2023)
- [Libraries' Metadata as Data in the Era of the Semantic Web: Modeling a Repository of Master Theses and PhD Dissertations for the Web of Data](https://mlsanity.com/paper/1609.03385/) (2016)

## Built on by (most cited first, 1 of 1)

- [The Impact of Modern AI in Metadata Management](https://mlsanity.com/paper/2501.16605/) (2025)

## Abstract (arXiv)

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.