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

arXiv cs.AI / 4/10/2026

📰 NewsDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The article introduces BDI-Kit, an extensible toolkit aimed at reducing bottlenecks in data harmonization caused by heterogeneous schemas and value conventions across domains.
BDI-Kit offers two interfaces: a Python API for developers to build and reuse harmonization pipelines, and an AI-assisted chat interface for domain experts to work via natural-language dialogue.
The demonstration emphasizes an iterative workflow that combines automated schema/value matching, AI-assisted reasoning, and user-driven refinement to validate and improve match quality.
Two showcased scenarios compare programmatic pipeline composition (examining intermediate outputs and reusing transformations) versus interactive conversational refinement using assistant suggestions.

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.