Research

As we're still setting up our website, this page shows only a small sample of our work.

As a member, you can submit your own work for inclusion in this list (email, DOI and brief description required).

  • Aligning Language Models with Human Values

    S. de Vries, D. Bakker · EACL 2025

    We introduce a framework for steering large language models toward explicitly stated human values rather than implicit preferences inferred from data. Across three benchmarks the method reduces value-laden errors without degrading task performance, and we discuss the governance questions that arise when "which values" becomes a design choice.

  • Auditing Algorithmic Decision-Making in the Public Sector

    J. Meijer, S. de Vries · AI & Society, 2025

    We report on audits of automated decision systems used by Dutch public bodies. Drawing on case studies in benefits and fraud detection, we identify recurring failure modes and propose a practical audit protocol that agencies can apply before deployment.

  • Transparency and Trust in Generative AI

    F. El Amrani, L. Hoffmann · ACM CHI 2024

    How much should a generative system reveal about its own uncertainty? In a study with 240 participants we find that calibrated confidence cues improve appropriate trust, while verbose explanations often backfire, and we offer design guidance for communicating model limitations.