Ali Mohammadi

About Me

I am a fourth-year Ph.D. student in Computer Science at the University of Maryland, Baltimore County (UMBC), where I am advised by Dr. Manas Gaur and Dr. Frank Ferraro. Previously, I completed my master's degree in artificial intelligence, which has equipped me with a strong foundation in AI. My research focuses on Natural Language Processing (NLP) and Machine Learning, with a specialization in the explainability and robustness of language models and large language models. I am passionate about advancing the understanding and application of NLP to create more interpretable and reliable AI systems.

I publish under the names Ali Mohammadi and Seyedali Mohammadi, reflecting my work across diverse collaborations and research topics.

View my Curriculum Vitae (CV) for more details.

Recent Papers

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions

Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba, Edward Raff, Ponnurangam Kumaraguru, Francis Ferraro, Manas Gaur
To appear in EMNLP 2025 (Main Conference). arXiv

LingVarBench: Benchmarking LLM for Automated Named Entity Recognition in Structured Synthetic Spoken Transcriptions

Seyedali Mohammadi, Manas Paldhe, Amit Chhabra
arXiv 2025, arXiv
Conducted as part of my summer internship at Infinitus Systems Inc.

Can LLMs obfuscate code? A systematic analysis of large language models into assembly code obfuscation.

Mohseni, S.^*, Mohammadi, S.^*, Tilwani, D., Ndawula, G. K., Vema, S., Saxena, Y., Raff, E., and Gaur, M.
AAAI 2025. AAAI
^*Equal contribution.

WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions

Seyedali Mohammadi, Edward Raff, Jinendra Malekar, Vedant Palit, Francis Ferraro, and Manas Gaur.
BlackboxNLP at EMNLP 2024. Association for Computational Linguistics

IoT-Based Preventive Mental Health Using Knowledge Graphs and Standards for Better Well-Being

Amelie Gyrard, Seyedali Mohammadi, Manas Gaur, Antonio Kung.
arXiv 2024. arXiv

Attribution in Scientific Literature: New Benchmark and Methods

Deepa Tilwani, Yash Saxena, Ali Mohammadi, Edward Raff, Amit Sheth, Srinivasan Parthasarathy, Manas Gaur.
arXiv 2024. arXiv

Previous Papers

A ROBUST GA/KNN BASED HYPOTHESIS VERIFICATION SYSTEM FOR VEHICLE DETECTION

Khairdoost, N., Pour, M. R. B., Mohammadi, S. A., Jajarm, M. H. International Journal of Artificial Intelligence & Applications, 2015.

Experience

Research Assistant

University of Maryland, Baltimore County
May 2023 – Present
Advised by Dr. Manas Gaur (Advisor) and Dr. Frank Ferraro (Co-advisor).

Member of Technical Team, Intern

Infinitus Systems, Inc., San Francisco, California
May - August 2025

Awards

2025

AAAI 2025 Travel Award.

2024

EMNLP BlackboxNLP Travel Award.

Invited Talk at ACM CIKM Workshop on Knowledge Graphs for Responsible AI.

UMBC Graduate Student Travel Award for EMNLP 2024.