Hello👋 I'm a recent graduate from the University of Kelaniya, where I completed my undergraduate degree in Computer Science with a specialization in Artificial Intelligence.

I am currently working as a Lecturer at the Department of Software Engineering within the Faculty of Computing and Technology at University of Kelaniya.

I am passionate about building LLMs that truly serve diverse global users representing low-resourced languages. I am interested in developing methods for LLMs to generate high-quality training data for low-resource languages by integrating iterative human feedback during the generation process, addressing the scarcity of naturally occurring text data. In addition to that, I want to create frameworks that use reasoning mechanisms to combine sparse feedback from expert and non-expert native speakers, maximizing the value of limited human input in low-resource contexts. Overall, I want to enable LLMs to capture linguistic and cultural nuances specific to underrepresented/low-resourced languages through targeted annotation and feedback strategies for domain-specific applications.

Update: I'm excited to share that my first research paper, "Subasa - Adapting Language Models for Low-Resourced Offensive Language Detection in Sinhala," based on my undergraduate thesis, has been published at NAACL 2025 SRW! (2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Student Research Workshop)

I'm always open to collaborative opportunities and discussions about innovative applications of AI and data science. Let's connect and explore how we can create impactful solutions together.