AI, safe for human beings

Publications

• July 2025
  NeoQA: Evidence-based Question Answering with Generated News Events
  Max Glockner, Xiang Jiang, Leonardo F. R. Ribeiro, Iryna Gurevych, Markus Dreyer
  ACL 2025 Findings (to appear)
  Paper: Link
  Code: GitHub
• July 2025
  Cultural Learning-Based Culture Adaptation of Language Models
  CC Liu, A Korhonen, I Gurevych
  ACL 2025 (to appear)
  Paper: Link
  Repository: GitHub
• July 2025
  Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art
  CC Liu, I Gurevych, A Korhonen
  TACL 2025 (to appear)
  Paper: Link
• July 2025
  Robust Utility-Preserving Text Anonymization Based on Large Language Models
  Tianyu Yang, Xiaodan Zhu, Iryna Gurevych
  ACL 2025 (to appear)
  Paper: Link
  Repository: GitHub
• July 2025
  ConInstruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities.
  Jiahui Geng, Thy Thy Tran, Preslav Nakov, Iryna Gurevych.
  ACL 2025 (to appear).
  Paper: Link
  Repository: GitHub
• July 2025
  Fine-grained Hallucination Detection and Mitigation in Long-form Question Answering.
  Rachneet Sachdeva, Yixiao Song, Mohit Iyyer, Iryna Gurevych.
  ACL 2025 Findings (to appear).
  Paper: Link
  Repository: GitHub
  Data: GitHub Data
• July 2025
  Community Moderation and the New Epistemology of Fact Checking on Social Media
  Isabelle Augenstein, Michiel Bakker, Tanmoy Chakraborty, David Corney, Emilio Ferrara, Iryna Gurevych, Scott Hale, Eduard Hovy, Heng Ji, Irene Larraz, Filippo Menczer, Preslav Nakov, Paolo Papotti, Dhruv Sahnan, Greta Warren, Giovanni Zagni
  Preprint 2025
  Paper: Link
  
• May 2025
  Grounding Fallacies: Misrepresenting Scientific Publications in Evidence
  Max Glockner, Yufang Hou, Preslav Nakov, Iryna Gurevych
  NAACL 2025
  Paper: Link
  Code: GitHub
• May 2025
  COVE: COntext and VEracity prediction for out-of-context images
  Jonathan Tonglet, Gabriel Thiem, Iryna Gurevych
  NAACL 2025
  Paper: Link
  Code: GitHub
• May 2025
  A Template Is All You Meme
  Luke Bates, Peter Ebert Christensen, Preslav Nakov, Iryna Gurevych
  NAACL 2025
  Paper: Link
  Code: GitHub
• May 2025
  Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling.
  Hovhannes Tamoyan, Subhabrata Dutta, Iryna Gurevych.
  Preprint under review.
  Paper: Link
  Repository: GitHub
• May 2025
  Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning.
  Jingcheng Niu, Subhabrata Dutta, Ahmed Elshabrawy, Harish Tayyar Madabushi, Iryna Gurevych.
  Preprint under review.
  Paper: Link
  Repository: GitHub
• Apr. 2025
  Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  Haritz Puerto, Martin Gubri, Sangdoo Yun, Seong Joon Oh
  Findings of NAACL 2025
  Paper: Link
  Code: GitHub
• Apr. 2025
  Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
  Jing Yang, Max Glockner, Anderson Rocha, Iryna Gurevych
  TACL 2025
  Paper: Link
  Code: GitHub
• Apr. 2025
  Differentially Private Steering for Large Language Model Alignment.
  Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal.
  ICLR 2025.
  Paper: Link
  Repository: GitHub
• Mar. 2025
  Protecting multimodal large language models against misleading visualizations
  Jonathan Tonglet, Tinne Tuytelaars, Marie-Francine Moens, Iryna Gurevych
  Preprint under review
  Paper: Link
  Code: GitHub
• Mar. 2025
  CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration.
  Rachneet Sachdeva, Martin Tutek, Iryna Gurevych. EACL 2024.
  Paper: Link
  Repository: GitHub
• Feb. 2025
  Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities
  Aishik Mandal, Tanmoy Chakraborty, Iryna Gurevych
  Preprint under review
  Paper: Link
• Jan. 2025
  Differentially Private Steering for Large Language Model Alignment
  Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal
  ICLR 2025
  Paper: Link
  Repository: GitHub
• Jan. 2025
  ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
  Indraneil Paul, Haoyi Yang, Goran Glavaš, Kristian Kersting, Iryna Gurevych
  ICLR 2025
  Paper: Link
  Code: GitHub
• Jan. 2025
  The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities.
  Irina Bigoulaeva, Harish Tayyar Madabushi, Iryna Gurevych.
  Preprint under review.
  Paper: Link
  Repository: GitHub
• Jan. 2025
  Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions.
  Rachneet Sachdeva, Rima Hazra, Iryna Gurevych.
  Preprint under review.
  Paper: Link
  Repository: GitHub
• Dec. 2024
  Preemptive Detection and Correction of Misaligned Actions in LLM Agents.
  Haishuo Fang, Xiaodan Zhu, Iryna Gurevych.
  Preprint under review.
  Paper: Link
• Nov. 2024
  “Image, Tell me your story!” Predicting the original meta-context of visual misinformation
  Jonathan Tonglet, Marie-Francine Moens, Iryna Gurevych
  EMNLP 2024
  Paper: Link
  Code: GitHub
  Data: Dataset
• Aug. 2024
  DOCE: Finding the Sweet Spot for Execution-Based Code Generation
  Haau-Sing Li, Patrick Fernandes, Iryna Gurevych, André F.T. Martins
  Preprint under review.
  Paper: Link
  Code: GitHub
• Aug. 2024
  IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
  Paul, Indraneil; Glavaš, Goran; Gurevych, Iryna
  ACL 2024
  Paper: Link
  Repository: GitHub
  Data: Dataset
• Aug. 2024
  MISSCI: Reconstructing Fallacies in Misrepresented Science
  Max Glockner, Yufang Hou, Preslav Nakov, Iryna Gurevych
  ACL 2024
  Paper: Link
  Code: GitHub
  Data: Dataset
• Aug. 2024
  Problem Solving Through Human-AI Preference-Based Cooperation
  Subhabrata Dutta, Timo Kaufmann, Goran Glavaš, Ivan Habernal, Kristian Kersting, Frauke Kreuter, Mira Mezini, Iryna Gurevych, Eyke Hüllermeier, Hinrich Schuetze
  Preprint under review.
  Paper: Link
• Aug. 2024
  Are Emergent Abilities in Large Language Models just In-Context Learning? Sheng Lu, Irina Bigoulaeva, Rachneet Sachdeva, Harish Tayyar Madabushi, Iryna Gurevych.
  ACL 2024
  Paper: Link
  Repository: GitHub
  Data: TUdatalib
• June 2024
  Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
  CC Liu, F Koto, T Baldwin, I Gurevych
  NAACL 2024
  Paper: Link
  Repository: GitHub
• June 2024
  How are Prompts Different in Terms of Sensitivity?
  Sheng Lu, Hendrik Schuff, and Iryna Gurevych.
  NAACL 2024.
  Paper: Link
  Repository: GitHub
• Mar. 2024
  Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification
  Luke Bates, Iryna Gurevych
  EACL 2024
  Paper: Link
  Code: GitHub
• Jan. 2024
  AmbiFC: Fact-Checking Ambiguous Claims with Evidence
  Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
  TACL 2024
  Paper: Link
  Code: GitHub
  Data: Google Drive
• July 2023
  Python Code Generation by Asking Clarification Questions
  Haau-Sing Li, Mohsen Mesgar, André F. T. Martins, Iryna Gurevych
  ACL 2023
  Paper: Link