Interactive Data Harmonization with LLM Agents: Opportunities and Challenges

2025/02/10 by Aécio Santos, Eduardo H. M. Pena, Santos, Aécio +5 · 1 voice · 2 citations
Computer Science · #cs.AI #cs.DB

paper · pdf · doi:10.48550/arxiv.2502.07132

Abstract

Data harmonization is an essential task that entails integrating datasets from diverse sources. Despite years of research in this area, it remains a time-consuming and challenging task due to schema mismatches, varying terminologies, and differences in data collection methodologies. This paper presents the case for agentic data harmonization as a means to both empower experts to harmonize their data and to streamline the process. We introduce Harmonia, a system that combines LLM-based reasoning, an interactive user interface, and a library of data harmonization primitives to automate the synthesis of data harmonization pipelines. We demonstrate Harmonia in a clinical data harmonization scenario, where it helps to interactively create reusable pipelines that map datasets to a standard format. Finally, we discuss challenges and open problems, and suggest research directions for advancing our vision.

Cited by

• Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare
• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

Discussions

• 📢 Tomorrow, I'll be presenting our new paper on LLM-based agents for interactive data integration at the #SIGMOD2025 NOVAS workshop. I'll also be in Berlin for the whole week, so please reach out if [bsky, 6 points, 1 comments]

Related

• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
• Integrating Information About Entities Progressively
• LLM/Agent-as-Data-Analyst: A Survey
• Speaking the Same Language: Leveraging LLMs in Standardizing Clinical Data for AI
• Towards Human-Guided, Data-Centric LLM Co-Pilots