KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat
KadiAssistant is a new AI tool designed to enhance information retrieval within the Kadi4Mat research data ecosystem. It aims to help researchers access and synthesize diverse and sensitive data across various disciplines. By integrating a privacy-preserving semantic search with a self-hosted large language model, KadiAssistant addresses the challenges of data privacy and complex access control.
- ▪KadiAssistant is integrated into the Kadi research data ecosystem to facilitate efficient information access.
- ▪The tool combines a large language model with a privacy-preserving semantic search to handle sensitive data.
- ▪It aims to lower access barriers for researchers and improve the Findable aspect of FAIR data principles.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Information Retrieval arXiv:2605.18850 (cs) [Submitted on 13 May 2026] Title:KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat Authors:Adrian Cierpka, Mohammad Shafiqul Islam, Johannes Steinhülb, Eric Dietriche Sesso Domtchoueng, Michael Selzer, Arnd Koeppe View a PDF of the paper titled KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat, by Adrian Cierpka and 5 other authors View PDF HTML (experimental) 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
