Selected as an Outstanding Reviewer at EMNLP 2025 (<1%); Paper 'A Causal Lens for Evaluating Faithfulness Metrics' accepted into EMNLP 2025; Paper 'INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models' accepted into ACL 2025; Paper 'Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion' accepted into EMNLP 2024
Research Experience
Summer 2025 internship at IFM MBZUAI Silicon Valley Lab, Mentor: Mikhail Yurochkin; Started internship at MBZUAI Institute of Foundation Model on May 23, 2025
Education
PhD: UNC Chapel Hill, Advisor: Shashank Srivastava; Bachelor's: Department of Computer Engineering, Boğaziçi University, Advisor: Pinar Yanardag
Background
Currently a fourth-year PhD student at UNC-Chapel Hill, with research interests in interpretable and explainable NLP, AI safety, reasoning, fairness, and robustness. The ultimate goal is to advance safe and transparent AI systems by deepening our understanding of black-box models.