My research focuses on leveraging language models to enable concurrent, embedded and transformative assessment processes for learners and their educational journeys.
Traditional assessment approaches are primarily summative, placing students in high-pressure exam situations that may not accurately reflect their abilities or learning progression. These assessments tend to follow a “one size fits all” model, neglecting the diverse needs and backgrounds of individual learners. Consequently, such approaches can contribute to educational inequities, diminish student motivation, overlook diversity, and offer insufficient feedback for guiding further learning. There’s a pressing need for a system that supports personalized formative assessment, promotes continuous educational growth, and remains scalable and efficient.
In contrast, the systems I develop create “bespoke assessments” tailored to each student’s unique educational context — considering their background, experiences, and current level of understanding. By providing real-time, relevant, and personalized feedback, these systems facilitate more accurate and supportive evaluation of student learning.
My research lies at the confluence of learning sciences, data science, and social learning, with a strong emphasis on design-based implementation. I focus on designing and deploying advanced educational technologies that enhance and support student learning experiences.