← People

Paul Röttger

Source-listed: Research group leader · Hasso-Plattner-Institut (HPI)

  • Multimodal AI
  • Language models
  • Speech and audio

Selected work

5
  1. HateCheck: Functional Tests for Hate Speech Detection ModelsFirst author · 2021
  2. XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language ModelsFirst author · 2024
  3. Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language ModelsFirst author · 2024
  4. The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language ModelsContributor · 2024
  5. MSTS: A Multimodal Safety Test Suite for Vision-Language ModelsFirst author · 2025