Kerem Zaman
PhD student at UNC Chapel Hill
UNC Chapel Hill
NC, USA
I’m currently a fourth-year PhD student at the UNC-Chapel Hill where I am advised by Shashank Srivastava. My research focuses on interpretable and explainable NLP, AI safety, reasoning, fairness, and robustness. My ultimate goal is to advance safe and transparent AI systems by deepening our understanding of black-box models.
I spent my summer (2025) at IFM MBZUAI Silicon Valley Lab with Mikhail Yurochkin. Before PhD, I earned my bachelor’s degree from the Department of Computer Engineering Boğaziçi University, where my thesis advisor was Pinar Yanardag.
news
| Jan 27, 2026 | Paper accepted into ICLR 2026! “DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing” [pdf] [website] |
|---|---|
| Dec 30, 2025 | New preprint! Is Chain-of-Thought really “not explainability”? [pdf] |
| Nov 7, 2025 | Selected as an Outstanding Reviewer at EMNLP 2025 (<1%)! |
| Sep 4, 2025 | Paper accepted into EMNLP 2025! “A Causal Lens for Evaluating Faithfulness Metrics “ [pdf] [code] |
| Jun 3, 2025 | Paper accepted into ACL 2025! “INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models” [pdf] [code] |