cs.AIApr 7, 2026

BDI-Kit Demo: A Toolkit for Programmable and Conversational Data Harmonization

Authors: Roque Lopez, Yurong Liu, Christos Koutras, Juliana Freire

Organizations: New York University New York, NY, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Data harmonization remains a major bottleneck for integrative analysis due to heterogeneity in schemas, value representations, and domain-specific conventions. BDI-Kit provides an extensible toolkit for schema and value matching. It exposes two complementary interfaces tailored to different user needs: a Python API enabling developers to construct harmonization pipelines programmatically, and an AI-assisted chat interface allowing domain experts to harmonize data through natural language dialogue. This demonstration showcases how users interact with BDI-Kit to iteratively explore, validate, and refine schema and value matches through a combination of automated matching, AI-assisted reasoning, and user-driven refinement. We present two scenarios: (i) using the Python API to programmatically compose primitives, examine intermediate outputs, and reuse transformations; and (ii) conversing with the AI assistant in natural language to access BDI-Kit's capabilities and iteratively refine outputs based on the assistant's suggestions.

Figures & tables

Figure 1. Users harmonize source data to target tables or data models via schema and value matching primitives, through a Python API or AI-assisted interfaces, producing a harmonized dataset and reusable specification.
Figure 2. Results of calling match_schema() and match_values() functions via the Python API.
Figure 3. BDI-Kit accessed through an AI agent orchestrating schema and value matching.
More in this topic

Data Integration

See all 15 papers

Explore similar work

CardsList

  1. MaDI-Bench: An End-to-End Data Integration Benchmark

    Jun 29, 2026Aaron Steiner, Ralph Peeters, Christian BizerBenchmark DesignData Integration

    Data and Web Science Group University of Mannheim Mannheim, Germany

  2. SINT-Flow: Schema Integration using Large Language Model Workflows

    Jul 27, 2026Keti Korini, Christian BizerSemantic MappingRelational Databases

    University of Mannheim Mannheim, Germany

  3. Automatic End-to-End Data Integration using Large Language Models

    Mar 11, 2026Aaron Steiner, Christian BizerData IntegrationData Fusion

    Data and Web Science Group, University of Mannheim, Mannheim, Germany