KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat

2026-05-13

AI Summary

This work addresses the challenges of information retrieval in interdisciplinary research—stemming from terminological heterogeneity, inconsistent data formats, and restricted access to privacy-sensitive data—by developing a conversational AI assistant integrated into the Kadi4Mat platform. The system uniquely incorporates privacy-by-design principles and fine-grained access control into a retrieval-augmented generation (RAG) architecture for scientific question answering. Leveraging a self-hosted large language model and privacy-preserving semantic search, it efficiently integrates multi-source heterogeneous data through the platform’s metadata interface. This approach significantly lowers technical barriers for researchers seeking access to sensitive, heterogeneous datasets, bridges terminological gaps across domains, enhances cross-disciplinary knowledge synthesis, and strengthens adherence to FAIR discoverability principles—all while rigorously safeguarding data privacy.

Abstract

We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently access, aggregate, and synthesize information from heterogeneous, privacy-sensitive research data. Interdisciplinary fields such as materials science bring together disciplines with their own terminology and standards. While this convergence fuels innovation, it also makes it increasingly difficult to connect and access knowledge, as data are distributed across disciplines, organizations, and individuals. For example, battery research combines electrochemical measurements, materials characterization data, physics-based simulations, and manufacturing parameters, each using different formats, vocabularies, and standards. Efficiently storing and sharing such heterogeneous data via research data platforms, such as Kadi4Mat, demands domain knowledge, technical expertise, and familiarity with metadata schemas and interfaces. Research data also vary in sensitivity: newly generated 'warm' data are often private, whereas published 'cold' data are usually openly accessible. The Kadi ecosystem offers fine-grained access control needed for sensitive data. A solution for efficient information retrieval in Kadi must therefore respect the fine-grained access permissions. To address these intertwined challenges of information retrieval, strong data privacy, and complex access control, KadiAssistant combines a self-hosted large language model (LLM) with a privacy-preserving semantic search, inspired by retrieval-augmented generation, that can access files and record metadata on Kadi. This allows the assistant to screen, aggregate, and structure information into a highly informative answer. KadiAssistant therefore bridges terminology and standards, lowers access barriers for researchers, and strengthens the Findable pillar of FAIR data principles.

Problem

• information retrieval
• heterogeneous research data
• privacy-sensitive data
• fine-grained access control
• interdisciplinary research

Innovation

• privacy-by-design
• retrieval-augmented generation
• fine-grained access control
• heterogeneous research data
• self-hosted LLM