Hi there! I’m Hiwot Belay, a Ph.D. student at Harvard’s Data to Actionable Knowledge Lab, advised by Finale Doshi-Velez.

Before starting my Ph.D., I completed my undergraduate studies in Computer Engineering at Benedict College. I also spent some time at IBM Research as a research software engineer.

Research Interests

My research focuses on Explainable Artificial Intelligence (XAI), with an emphasis on developing transparent and trustworthy explanations for machine learning models. I’m particularly interested in designing explanation methods that adapt to the needs of the end user, and that support understanding and more informed decision-making.

📄 Publications

• Optimizing Explanations: Nuances Matter When Evaluation Metrics Become Loss Functions
  Jonas B Raedler, H. Tadesse, W. Pan, F. Doshi-Velez
  ICML Workshop on Methods and Opportunities at Small Scale (MOSS), 2025
• Transparent Trade-offs between Properties of Explanations
  H Tadesse, A Hüyük, Y Yacoby, W Pan, and F Doshi-Velez
  Uncertainity in Artificial Intelligence, UAI 2025
• Directly Optimizing Explanations
  H Tadesse, A Hüyük, Y Yacoby, W Pan, and F Doshi-Velez
  ICML Workshop on Humans, Algorithmic Decision-Making and Society: Modeling Interactions and Impact, 2024
• Variational Exploration Module VEM: A Cloud-Native Optimization and Validation Tool for Geospatial Modeling and AI Workflows
  Julian Kuehnert, Hiwot Tadesse, Chris Dearden, Rosie Lickorish, Paolo Fraccaro, Anne Jones, Blair Edwards, Sekou L Remy, Peter Melling, Tim Culmer Pre-print, 2023

  📬 Get in Touch

  Feel free to reach out via Email