Mohammadamin Shafiei

Publications

*: equal contribution

• TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering 2025
  Mohammadamin Shafiei*, Hamidreza Saffari*, Mohammad Taher Pilehvar, Alessandro Raganato ArXiv [paper]
• Farsi Physical Commonsense Reasoning Dataset
  Hamidreza Saffari*, Mohammadamin Shafiei* ArXiv [paper]
• LingAlign: A Multilingual, Multidimensional Benchmark for Evaluating LLM Alignment Variability
  Mohammadamin Shafiei*, Hamidreza Saffari*, Nafise Sadat Moosavi ArXiv [paper]
• Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language
  Hamidreza Saffari*, Mohammadamin Shafiei*, Hezhao Zhang*, Lasana Harris, Nafise Sadat Moosavi ArXiv [paper]
• More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning
  Mohammadamin Shafiei*, Hamidreza Saffari*, Nafise Sadat Moosavi ArXiv [paper]
• Measuring Gender Bias in the Farsi Language
  Hamidreza Saffari*, Mohammadamin Shafiei*, Donya Rooein, Debora Nozza GeBNLP @ ACL 2025 [paper]
• MultiHoax: Benchmarking LLMs on false-premise multi-hop reasoning questions
  Mohammadamin Shafiei*, Hamidreza Saffari*, Nafise Sadat Moosavi ACL2025, Findings [paper]
• Can I introduce my boyfriend to my grandmother? Evaluating Large Language Models' Capabilities on Iranian Social Norm Classification
  Hamidreza Saffari*, Mohammadamin Shafiei*, Donya Rooein*, Francesco Pierri, Debora Nozza NAACL2025, Findings [paper]
• Not All Jokes Land: Evaluating Large Language Models' Understanding of Workplace Humor
  Mohammadamin Shafiei*, Hamidreza Saffari* ArXiv [paper]