Using ChatGPT to refine draft conceptual schemata in supply-driven design of multidimensional cubes

2025-02-04

AI Summary

In supply-driven multidimensional cube conceptual design, pattern refinement heavily relies on manual intervention by designers, hindering automation. Method: This paper systematically investigates, for the first time, the feasibility of leveraging large language models (LLMs) to assist end users in autonomously performing refinement within the Dimensional Fact Model (DFM) framework. Using GPT-4o, we design semantics-aware prompts to construct an end-to-end semi-automated refinement pipeline. Results: Experiments show a significant improvement in refinement accuracy; residual errors are rectified with a single follow-up prompt. End users retain full control throughout the process, drastically reducing dependence on expert designers. This work not only validates LLMs’ effectiveness in multidimensional model refinement but also establishes a novel user-centered, low-barrier, high-semantic-fidelity interactive modeling paradigm.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Refinement is a critical step in supply-driven conceptual design of multidimensional cubes because it can hardly be automated. In fact, it includes steps such as the labeling of attributes as descriptive and the removal of uninteresting attributes, thus relying on the end-users' requirements on the one hand, and on the semantics of measures, dimensions, and attributes on the other. As a consequence, it is normally carried out manually by designers in close collaboration with end-users. The goal of this work is to check whether LLMs can act as facilitators for the refinement task, so as to let it be carried out entirely -- or mostly -- by end-users. The Dimensional Fact Model is the target formalism for our study; as a representative LLM, we use ChatGPT's model GPT-4o. To achieve our goal, we formulate three research questions aimed at (i) understanding the basic competences of ChatGPT in multidimensional modeling; (ii) understanding the basic competences of ChatGPT in refinement; and (iii) investigating if the latter can be improved via prompt engineering. The results of our experiments show that, indeed, a careful prompt engineering can significantly improve the accuracy of refinement, and that the residual errors can quickly be fixed via one additional prompt. However, we conclude that, at present, some involvement of designers in refinement is still necessary to ensure the validity of the refined schemata.

Problem

• Using ChatGPT to automate refinement in multidimensional cubes.
• Exploring ChatGPT's competence in multidimensional modeling tasks.
• Assessing prompt engineering's impact on refinement accuracy.

Innovation

• ChatGPT enhances schema refinement
• Prompt engineering boosts accuracy
• Minimal designer involvement ensures validity