Paul Röttger

Venues

Frequent coauthors

Papers

1. Bias in the East, Bias in the West: A Bilingual Analysis of LLM Political Bias on U.S.- and China-Related Issues
   EACL 2026 ·

   Ying Ying Lim

   DBLP profile ↗ORCID search ↗
2. The Pluralistic Moral Gap: Understanding Moral Judgment and Value Differences between Humans and Large Language Models
   EACL 2026 ·

   Giuseppe Russo

   DBLP profile ↗ORCID search ↗
3. AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
   NAACL 2025 ·

   Shamsuddeen Hassan Muhammad

   DBLP profile ↗ORCID search ↗
4. Around the World in 24 Hours: Probing LLM Knowledge of Time and Place
   ACL 2025 ·

   Carolin Holtermann

   DBLP profile ↗ORCID search ↗
5. Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions
   ACL 2025 ·

   Matthias Orlikowski

   DBLP profile ↗ORCID search ↗
6. HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter
   ACL 2025 ·

   Manuel Tonneau

   DBLP profile ↗ORCID search ↗
7. Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce Them
   EMNLP 2025 ·

   Emanuele Moscato

   DBLP profile ↗ORCID search ↗
8. Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
   EMNLP 2025 ·

   Pedro Henrique Luz de Araujo

   DBLP profile ↗ORCID search ↗
9. SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
   AAAI 2025 · Paul Röttger
10. Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations
    NAACL 2025 ·

    Yong Cao

    DBLP profile ↗ORCID search ↗
11. Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
    ICLR 2025 ·

    Xinpeng Wang

    DBLP profile ↗ORCID search ↗
12. TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
    EMNLP 2025 ·

    Dominik Meier

    DBLP profile ↗ORCID search ↗
13. "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
    ACL 2024 ·

    Xinpeng Wang

    DBLP profile ↗ORCID search ↗
14. Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models
    ACL 2024 ·

    Fabio Pernisi

    DBLP profile ↗ORCID search ↗
15. Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ
    ACL 2024 ·

    Carolin Holtermann

    DBLP profile ↗ORCID search ↗
16. Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset
    NAACL 2024 ·

    Janis Goldzycher

    DBLP profile ↗ORCID search ↗
17. Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
    ACL 2024 · Paul Röttger
18. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI
    ICML 2024 ·

    Francisco Eiras

    DBLP profile ↗ORCID search ↗
19. Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
    ICLR 2024 ·

    Federico Bianchi

    DBLP profile ↗ORCID search ↗
20. The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
    NeurIPS 2024 ·

    Hannah Rose Kirk

    DBLP profile ↗ORCID search ↗
21. XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
    NAACL 2024 · Paul Röttger