Flavio De Paoli

Marco Ripamonti, Flavio De Paoli, Matteo Palmonari

The large availability of datasets fosters the use of \acrshort{ml} and \acrshort{ai} technologies to gather insights, study trends, and predict unseen behaviours out of the world of data. Today, gathering and integrating data from different sources is mainly a manual activity that requires the knowledge of expert users at an high cost in terms of both time and money. It is, therefore, necessary to make the process of gathering and linking data from many different sources affordable to make datasets ready to perform the desired analysis. In this work, we propose the development of a comprehensive framework, named SemTUI, to make the enrichment process flexible, complete, and effective through the use of semantics. The approach is to promote fast integration of external services to perform enrichment tasks such as reconciliation and extension; and to provide users with a graphical interface to support additional tasks, such as refinement to correct ambiguous results provided by automatic enrichment algorithms. A task-driven user evaluation proved SemTUI to be understandable, usable, and capable of achieving table enrichment with little effort and time with user tests that involved people with different skills and experiences.

Abubakari Alidu, Michele Ciavotta, Flavio DePaoli

Developing reliable data enrichment pipelines demands significant engineering expertise. We present Prompt2DAG, a methodology that transforms natural language descriptions into executable Apache Airflow DAGs. We evaluate four generation approaches -- Direct, LLM-only, Hybrid, and Template-based -- across 260 experiments using thirteen LLMs and five case studies to identify optimal strategies for production-grade automation. Performance is measured using a penalized scoring framework that combines reliability with code quality (SAT), structural integrity (DST), and executability (PCT). The Hybrid approach emerges as the optimal generative method, achieving a 78.5% success rate with robust quality scores (SAT: 6.79, DST: 7.67, PCT: 7.76). This significantly outperforms the LLM-only (66.2% success) and Direct (29.2% success) methods. Our findings show that reliability, not intrinsic code quality, is the primary differentiator. Cost-effectiveness analysis reveals the Hybrid method is over twice as efficient as Direct prompting per successful DAG. We conclude that a structured, hybrid approach is essential for balancing flexibility and reliability in automated workflow generation, offering a viable path to democratize data pipeline development.