About me
Hi! I am a PhD Candidate at the Department of Mathematics and Computer Science (IMADA), University of Southern Denmark (SDU) advised by Prof. Peter Schneider-Kamp and Prof. Lukas Galke Poech.
My research focuses on interpretability, NLP, and AI safety. I am particularly interested in understanding how large language models represent knowledge internally and how different concepts and behaviors emerge inside these models.
Before joining SDU, I completed my MSc in Artificial Intelligence at the University of Tehran, under the supervision of Prof. Yadollah Yaghoobzadeh.
Broadly, I enjoy research that tries to look “under the hood” of modern AI systems: not only asking what models can do, but also how and why they do it.
Feel free to email me if you have questions about my work, research collaborations, or related academic topics.
Research Interests
My research interests span across several areas within NLP, including:
- Multilingual NLP
- Interpretability & Explainibility
- Multimodal Reasoning
- Evaluation and Benchmarking
- Multi-Agent Systems
News
- Jan 2026: Our paper "A Computational Approach to Language Contact – A Case Study of Persian" is now available on arXiv! [paper] [code]
- Jan 2026: Our paper "APARSIN: A Multi-Variety Sentiment and Translation Benchmark for Iranic Languages" is now available on arXiv! [paper] [code]
- Oct 2025: Our paper "Isolating Culture Neurons in Multilingual Large Language Models" has been accepted for presentation at IJCNLP-AACL 2025! [paper] [code]
- Dec 2024: Our paper "Comparative Study of Multilingual Idioms and Similes in Large Language Models" has been accepted for presentation at COLING 2025! [paper] [code]
- Feb 2024: Our paper "Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT" has been accepted for presentation at LREC-CoLing 2024! [paper] [code]