Stefano Rizzi

Retrieval-Augmented Generation (RAG) systems are increasingly deployed on large-scale document collections, often comprising millions of documents and tens of millions of text chunks. In industrial-scale retrieval platforms, scalability is typically addressed through horizontal sharding and a combination of Approximate Nearest-Neighbor search, hybrid indexing, and optimized metadata filtering. Although effective from an efficiency perspective, these mechanisms rely on bottom-up, similarity-driven organization and lack a conceptual rationale for corpus partitioning. In this paper, we claim that the design of large-scale RAG systems may benefit from the combination of two orthogonal strategies: semantic clustering, which optimizes locality in embedding space, and multidimensional partitioning, which governs where retrieval should occur based on conceptual dimensions such as time and organizational context. Although such dimensions are already implicitly present in current systems, they are used in an ad hoc and poorly structured manner. We propose the Dimensional Fact Model (DFM) as a conceptual framework to guide the design of multidimensional partitions for RAG corpora. The DFM provides a principled way to reason about facts, dimensions, hierarchies, and granularity in retrieval-oriented settings. This framework naturally supports hierarchical routing and controlled fallback strategies, ensuring that retrieval remains robust even in the presence of incomplete metadata, while transforming the search process from a 'black-box' similarity matching into a governable and deterministic workflow. This work is intended as a position paper; its goal is to bridge the gap between OLAP-style multidimensional modeling and modern RAG architectures, and to stimulate further research on principled, explainable, and governable retrieval strategies at scale.

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.

Information visualization plays a key role in business intelligence analytics. With ever larger amounts of data that need to be interpreted, using the right visualizations is crucial in order to understand the underlying patterns and results obtained by analysis algorithms. Despite its importance, defining the right visualization is still a challenging task. Business users are rarely experts in information visualization, and they may not exactly know the most adequate visualization tools or patterns for their goals. Consequently, misinterpreted graphs and wrong results can be obtained, leading to missed opportunities and significant losses for companies. The main problem underneath is a lack of tools and methodologies that allow non-expert users to define their visualization and data analysis goals in business terms. In order to tackle this problem, we present an iterative goal-oriented approach based on the i* language for the automatic derivation of data visualizations. Our approach links non-expert user requirements to the data to be analyzed, choosing the most suited visualization techniques in a semi-automatic way. The great advantage of our proposal is that we provide non-expert users with the best suited visualizations according to their information needs and their data with little effort and without requiring expertise in information visualization.