| Home | | Teaching | | Awards | Publications |

Publications

• Mina Arzaghi, Florian Carichon, and Golnoosh Farnadi
  “Understanding Intrinsic Socioeconomic Biases in Large Language Models.”
  Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, Vol. 7, 2024.
  🏆 Presented at AAAI/ACM Conference on AI, Ethics, and Society AIES 2024.
  🏆 Presented at the Women in Machine Learning Workshop WiML Workshop @ NeurIPS 2024.
  🎖️ Received Honourable Mention at the SSC 2025 Annual Meeting (Business & Industrial Statistics Section).
  📄 Read the full paper

• Mina Arzaghi
  “Advancing Fairness in Generative AI Through Intrinsic and Extrinsic Bias Evaluation and Mitigation”
  Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, Vol. 8 No.3, 2025.
  🏆 Presented at AAAI/ACM Conference on AI, Ethics, and Society AIES 2025.
  🏆 Presented at ACM Conference on Fairness, Accountability, and Transparency ACM FAccT 2025.
  📄 Read the full paper

• Mina Arzaghi, Alireza Dehghanpour Farashah, Florian Carichon, and Golnoosh Farnadi
  “Intrinsic Meets Extrinsic Fairness: Assessing the Downstream Impact of Bias Mitigation in Large Language Models”
  📄 Read the full paper

📚 See all my publications on Google Scholar.