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 IssuesBibTeX ⧉
   EACL 2026 ·

   Ying Ying Lim

   , Paul Röttger
2. The Pluralistic Moral Gap: Understanding Moral Judgment and Value Differences between Humans and Large Language ModelsBibTeX ⧉
   EACL 2026 ·

   Giuseppe Russo

   ,

   Debora Nozza

   , Paul Röttger,

   Dirk Hovy
3. AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African LanguagesBibTeX ⧉
   NAACL 2025 ·

   Shamsuddeen Hassan Muhammad

   ,

   Idris Abdulmumin

   ,

   Abinew Ali Ayele

   ,

   David Ifeoluwa Adelani

   ,

   Ibrahim Said Ahmad

   ,

   Saminu Mohammad Aliyu

   , Paul Röttger,

   Abigail Oppong

   ,

   Andiswa Bukula

   ,

   Chiamaka Ijeoma Chukwuneke

   ,

   Ebrahim Chekol Jibril

   ,

   Elyas Abdi Ismail

   ,

   Esubalew Alemneh

   ,

   Hagos Tesfahun Gebremichael

   ,

   Lukman Jibril Aliyu

   ,

   Meriem Beloucif

   ,

   Oumaima Hourrane

   ,

   Rooweither Mabuya

   ,

   Salomey Osei

   ,

   Samuel Rutunda

   ,

   Tadesse Destaw Belay

   ,

   Tadesse Kebede Guge

   ,

   Tesfa Tegegne Asfaw

   ,

   Lilian Diana Awuor Wanzare

   ,

   Nelson Odhiambo Onyango

   ,

   Seid Muhie Yimam

   ,

   Nedjma Ousidhoum
4. Around the World in 24 Hours: Probing LLM Knowledge of Time and PlaceBibTeX ⧉
   ACL 2025 ·

   Carolin Holtermann

   , Paul Röttger,

   Anne Lauscher
5. Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text PerceptionsBibTeX ⧉
   ACL 2025 ·

   Matthias Orlikowski

   ,

   Jiaxin Pei

   , Paul Röttger,

   Philipp Cimiano

   ,

   David Jurgens

   ,

   Dirk Hovy
6. HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on TwitterBibTeX ⧉
   ACL 2025 ·

   Manuel Tonneau

   ,

   Diyi Liu

   ,

   Niyati Malhotra

   ,

   Scott A. Hale

   ,

   Samuel Fraiberger

   ,

   Víctor Orozco-Olvera

   , Paul Röttger
7. Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce ThemBibTeX ⧉
   EMNLP 2025 ·

   Emanuele Moscato

   ,

   Tiancheng Hu

   ,

   Matthias Orlikowski

   , Paul Röttger,

   Debora Nozza
8. Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task PerformanceBibTeX ⧉
   EMNLP 2025 ·

   Pedro Henrique Luz de Araujo

   , Paul Röttger,

   Dirk Hovy

   ,

   Benjamin Roth
9. SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model SafetyBibTeX ⧉
   AAAI 2025 · Paul Röttger,

   Fabio Pernisi

   ,

   Bertie Vidgen

   ,

   Dirk Hovy
10. Specializing Large Language Models to Simulate Survey Response Distributions for Global PopulationsBibTeX ⧉
    NAACL 2025 ·

    Yong Cao

    ,

    Haijiang Liu

    ,

    Arnav Arora

    ,

    Isabelle Augenstein

    , Paul Röttger,

    Daniel Hershcovich
11. Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector AblationBibTeX ⧉
    ICLR 2025 ·

    Xinpeng Wang

    ,

    Chengzhi Hu

    , Paul Röttger,

    Barbara Plank
12. TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking AgentBibTeX ⧉
    EMNLP 2025 ·

    Dominik Meier

    ,

    Jan Philip Wahle

    , Paul Röttger,

    Terry Ruas

    ,

    Bela Gipp
13. "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language ModelsBibTeX ⧉
    ACL 2024 ·

    Xinpeng Wang

    ,

    Bolei Ma

    ,

    Chengzhi Hu

    ,

    Leon Weber-Genzel

    , Paul Röttger,

    Frauke Kreuter

    ,

    Dirk Hovy

    ,

    Barbara Plank
14. Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language ModelsBibTeX ⧉
    ACL 2024 ·

    Fabio Pernisi

    ,

    Dirk Hovy

    , Paul Röttger
15. Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQBibTeX ⧉
    ACL 2024 ·

    Carolin Holtermann

    , Paul Röttger,

    Timm Dill

    ,

    Anne Lauscher
16. Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech DatasetBibTeX ⧉
    NAACL 2024 ·

    Janis Goldzycher

    , Paul Röttger,

    Gerold Schneider
17. Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language ModelsBibTeX ⧉
    ACL 2024 · Paul Röttger,

    Valentin Hofmann

    ,

    Valentina Pyatkin

    ,

    Musashi Hinck

    ,

    Hannah Kirk

    ,

    Hinrich Schütze

    ,

    Dirk Hovy
18. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AIBibTeX ⧉
    ICML 2024 ·

    Francisco Eiras

    ,

    Aleksandar Petrov

    ,

    Bertie Vidgen

    ,

    Christian Schröder de Witt

    ,

    Fabio Pizzati

    ,

    Katherine Elkins

    ,

    Supratik Mukhopadhyay

    ,

    Adel Bibi

    ,

    Botos Csaba

    ,

    Fabro Steibel

    ,

    Fazl Barez

    ,

    Genevieve Smith

    ,

    Gianluca Guadagni

    ,

    Jon Chun

    ,

    Jordi Cabot

    ,

    Joseph Marvin Imperial

    ,

    Juan A. Nolazco-Flores

    ,

    Lori Landay

    ,

    Matthew Thomas Jackson

    , Paul Röttger,

    Philip H. S. Torr

    ,

    Trevor Darrell

    ,

    Yong Suk Lee

    ,

    Jakob N. Foerster
19. Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow InstructionsBibTeX ⧉
    ICLR 2024 ·

    Federico Bianchi

    ,

    Mirac Suzgun

    ,

    Giuseppe Attanasio

    , Paul Röttger,

    Dan Jurafsky

    ,

    Tatsunori Hashimoto

    ,

    James Zou
20. The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language ModelsBibTeX ⧉
    NeurIPS 2024 ·

    Hannah Rose Kirk

    ,

    Alexander Whitefield

    , Paul Röttger,

    Andrew M. Bean

    ,

    Katerina Margatina

    ,

    Rafael Mosquera Gómez

    ,

    Juan Ciro

    ,

    Max Bartolo

    ,

    Adina Williams

    ,

    He He

    ,

    Bertie Vidgen

    ,

    Scott Hale
21. XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language ModelsBibTeX ⧉
    NAACL 2024 · Paul Röttger,

    Hannah Kirk

    ,

    Bertie Vidgen

    ,

    Giuseppe Attanasio

    ,

    Federico Bianchi

    ,

    Dirk Hovy