Proceed to contents
Part of the 'Blueprint' trajectory on AI for professionals in higher education

Processing Sensitive Text Data with Open-Source AI Tools

Do you work with sensitive text data (e.g., research proposals, participant or patient data, HR data...) and therefore hesitate to use AI tools such as ChatGPT? Are you unsure about what really happens to your data and concerned about privacy and security? And most importantly, are you looking for a safer alternative?

Practical information:

6 hours
Your choice (in-company)
Mixed Dutch & English
Target audience: Researchers handling sensitive text data, authors of grant proposals, authors of intellectual property

Want to register?

  • Prerequisites: Technical version: basic programming skills in Python / Non-technical version: no prerequisites
  • Price: to be agreed
More info & registration ⇗

Do you work with sensitive text data (e.g., research proposals, participant or patient data, HR data...) and therefore hesitate to use AI tools such as ChatGPT? Are you unsure about what really happens to your data and concerned about privacy and security? And most importantly, are you looking for a safer alternative?

In this course, consisting of a lecture and workshop, you’ll explore open-source AI tools to handle sensitive text data in a safer way. You’ll compare their capabilities, potential dangers and performance with those of large commercial tools. Finally, you’ll cover case studies that you can then apply to your own data.

Note that this course can now be booked in two different versions, depending on the audience's prior knowledge and technical skills:

- technical version: for people with (basic) programming skills

- non-technical version: no prerequisites

(This session had a slightly different title before: "Processing Sensitive Text Data Using Open-Source Large Language Models". The contents of the session have not changed!)

Teacher / speaker

Pieter Fivez

Pieter Fivez holds a PhD in Linguistics from the University of Antwerp, focusing on machine learning of semantic representations of biomedical text. He currently works as a postdoctoral researcher at the University of Antwerp, where he coordinates the Antwerp Text Mining Centre (TEXTUA).

Learning Trajectory on Generative AI for Professionals in Higher Education

This is a suggestion for a learning trajectory on generative AI, targeted at professionals working in higher education (e.g., researchers, lecturers, administrative and technical staff, policymakers). The learning modules were carefully selected by VAIA to create a holistic and realistic starting point for educating this target group on GenAI. This trajectory gets updated regularly!

Life and Material Science Bootcamp on SuperMUC-NG Phase 2

17 September 2026

Bootcamp - München - LRZ

AI for Science

21 September 2026

Zomerschool - Duitsland - IWR