PhD Student
Chair of Software Engineering
Ruhr University Bochum
Bochum, Germany
About Me
My name is Abdullah Al Sefat, and I am a Researcher and PhD candidate at the Chair of Software Engineering at Ruhr University Bochum. My research focuses on the role of Large Language Models (LLMs) in Software Engineering practices, with an emphasis on how data-driven and language-based models can support, automate, and improve real-world software development workflows.
I have completed my B.Sc. in Computer Science & Engineering (CSE) from Ahsanullah University of Science and Technology (AUST), specializing on Software Engineering and Computer Networks. I hold a Master’s degree in Informatics from the Technical University of Munich (TUM), specializing in Deep Learning and Natural Language Processing, and have prior research experience in areas such as transformer-based models, under-resourced NLP, and applied NLP systems. Before starting my role at Ruhr University Bochum, I worked on research projects spanning academic and applied settings, including Legal AI and large-scale text analysis.
My current work explores how LLMs can be reliably integrated into software engineering tasks; such as code understanding, documentation, testing, and developer support; while addressing challenges related to robustness, evaluation, and practical usability. I am particularly interested in bridging the gap between machine learning research and software engineering practice, with the goal of building tools that are both technically sound and developer-centric.
Contact
Office: MC 4.102
E-Mail: abdullah[dot]sefat[at]ruhr-uni-bochum.de
Research Focus
- Large Language Models (LLMs) for Software Engineering and Developer Support
- Natural Language Processing (NLP) for Code, Software Artifacts, and Technical Text
- LLM based Program Understanding, Code Summarization, and Documentation Generation
- Robustness, Evaluation, and Limitations of LLMs in technical and social settings
- Applied Machine Learning for Real-World Text and Language-Centered Systems
Publications
- Abdullah Al Sefat, Amir Hossein Kargaran, François Yvon, Hinrich Schütze. GlotWeb: Web Indexing
for Minority Languages. ACM The Web Conference (WWW 2026), Dubai, UAE, (Accepted To be published) - Abdullah Al Sefat. 2025. BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali. In Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025), pages 58–77, Mumbai, India. Association for Computational Linguistics.
- Md. Samiul Alam, Kazi Kalpoma, Md. Sanaul Karim, Abdullah Al Sefat, Jun-ichi Kudoh. Boro Rice
Yield Estimation Model Using MODIS NDVI Data for Bangladesh. IGARSS 2019, IEEE International
Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019. - G. M. Rasiqul Islam Rasiq, Abdullah Al Sefat, M. M. Fahim Hasnain. Mobile Based MCQ Answer
Sheet Analysis and Evaluation Application. 2019 8th International Conference on System Modeling
and Advancement in Research Trends (SMART), Moradabad, India, 2019. - G. M. Rasiqul Islam Rasiq, Abdullah Al Sefat, Tanjila Hossain, Md. Israt-E-Hasan Munna, Jubayeath
Jahan Jisha, Md. Moinul Hoque. Question Answering System over Linked Data: A Detailed Survey.
ABC Research Alert, 8(1), pp. 32–47, April 2020.