AI-assisted JSON Schema Creation and Mapping
Felix Neubauer, J\"urgen Pleiss, Benjamin Uekermann

TL;DR
This paper introduces a hybrid AI approach that combines large language models with deterministic methods to facilitate JSON Schema creation, modification, and mapping from natural language, making data modeling accessible to non-experts.
Contribution
It presents a novel hybrid system integrating LLMs and deterministic techniques for schema creation and mapping, implemented in an open-source tool for easier data integration.
Findings
Effective schema creation from natural language inputs.
Reliable schema mapping across heterogeneous data formats.
Demonstrated application in chemistry data management.
Abstract
Model-Driven Engineering (MDE) places models at the core of system and data engineering processes. In the context of research data, these models are typically expressed as schemas that define the structure and semantics of datasets. However, many domains still lack standardized models, and creating them remains a significant barrier, especially for non-experts. We present a hybrid approach that combines large language models (LLMs) with deterministic techniques to enable JSON Schema creation, modification, and schema mapping based on natural language inputs by the user. These capabilities are integrated into the open-source tool MetaConfigurator, which already provides visual model editing, validation, code generation, and form generation from models. For data integration, we generate schema mappings from heterogeneous JSON, CSV, XML, and YAML data using LLMs, while ensuring scalability…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
