Bashar Alhafni

Hi! I am an Assistant Professor of Natural Language Processing at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where I lead the Arabic AI Modeling (Aram) Lab. My research focuses on Arabic NLP with an emphasis on three interconnected themes: advancing educational Arabic NLP, developing personalized and human-centered language technologies, and understanding how linguistic representation shapes model behavior. At its core, my work aims to build Arabic NLP systems that enhance learning experiences and contribute to social good.

Before joining MBZUAI, I completed my Ph.D. in Computer Science from New York University (NYU), where I was advised by Prof. Nizar Habash.
My dissertation focused on controlled Arabic natural language generation with applications in AI for education and social impact. Before that, I earned my Master’s from the University of Southern California (USC), where I worked at ISI on low-resource machine translation and event relation extraction. I hold a Bachelor’s degree in Computer Science and Mathematics from the University of Bridgeport.
In addition to my academic work, I have held applied NLP research roles at Grammarly and Dataminr, where I contributed to projects in personalized text generation, summarization, and multilingual NLP.

I am always looking to work with motivated students and postdocs. Feel free to reach out if you are interested in applying to MBZUAI.

News

07/2025 I am excited to join MBZUAI as an Assistant Professor of Natural Language Processing. I am currently looking for students and postdocs to join my lab!
05/2025 Our paper on Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study has been accepted to ACL.
04/2025 I have successfully defended my Ph.D. dissertation titled Controlled Natural Language Generation for Morphologically Rich Languages: The Case of Arabic. Many thanks so my committee members: Ted Birscoe, Kyunghyun Cho, Mona Diab, Nizar Habash, He He, and Julia Stoyanovich.
04/2025 Our paper, ARWI: Arabic Write and Improve, won the diverstiy award at the In2Writing workshop at NAACL 2025 🏆
01/2025 Co-organizing the BEA 2025 workshop at ACL 2025.
09/2024 Gave a talk at the National Research Council Canada (NRC-CNRC) on Controlled User-Centric Natural Language Generation for Morphologically Rich Languages: The Case of Arabic.
09/2024 Presenting a tutorial at COLING 2025 on LLMs in Education: Novel Perspectives, Challenges, and Opportunities with Sowmya Vajjala, Stefano Bannò, Kaushal Kumar Maurya, and Ekaterina Kochmar (tutorial website).
04/2024 Co-organizing the 2nd Arabic Natural Language Processing Conference (ArabicNLP 2024) at ACL 2024!

Selected Publications

  1. ACL
    Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study
    Alhafni, Bashar, and Habash, Nizar
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics
    PDF Code
  2. In2Writing
    ARWI: Arabic Write and Improve 🏆
    Chirkunov, Kirill, Alhafni, Bashar, Qwaider, Chatrine, Habash, Nizar, and Briscoe, Ted
    In Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants. NAACL 2025
    PDF Demo
  3. arXiv
    A Tale of Two Scripts: Transliteration and Post-Correction for Judeo-Arabic
    Gonzalez, Juan Moreno, Alhafni, Bashar, and Habash, Nizar
    arXiv preprint
    PDF
  4. ArabicNLP
    Exploiting Dialect Identification in Automatic Dialectal Text Normalization
    Alhafni, Bashar, Al-Towaity, Sarah, Fawzy, Ziyad, Nassar, Fatema, Eryani, Fadhl, Bouamor, Houda, and Habash, Nizar
    In Proceedings of the Second Arabic Natural Language Processing Conference. ACL 2024
    PDF Code Talk
  5. LREC-COLING
    The SAMER Arabic Text Simplification Corpus
    Alhafni, Bashar, Hazim, Reem, Piñeros Liberato, Juan, Al Khalil, Muhamed, and Habash, Nizar
    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
    PDF Data Talk
  6. NAACL
    mEdIT: Multilingual Text Editing via Instruction Tuning
    Raheja, Vipul, Alikaniotis, Dimitris, Kulkarni, Vivek, Alhafni, Bashar, and Kumar, Dhruv
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
    PDF Code
  7. Personalize
    Personalized Text Generation with Fine-Grained Linguistic Control
    Alhafni, Bashar, Kulkarni, Vivek, Kumar, Dhruv, and Raheja, Vipul
    In Proceedings of the 1st Workshop on Personalization of Generative AI Systems. EACL 2024
    PDF Code
  8. EMNLP
    Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation
    Alhafni, Bashar, Inoue, Go, Khairallah, Christian, and Habash, Nizar
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
    PDF Code Talk
  9. NAACL
    User-Centric Gender Rewriting
    Alhafni, Bashar, Habash, Nizar, and Bouamor, Houda
    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics
    PDF Code Talk
  10. LREC
    The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses
    Alhafni, Bashar, Habash, Nizar, and Bouamor, Houda
    In Proceedings of the 13th Language Resources and Evaluation Conference
    PDF Data