-
GenAI Role-Play for Professional Education: Investigating and Evaluating Generative AI-Enabled Role-Play for Competency-Based Education and Professional Readiness
•
Evaluating whether AI-powered role-play simulations can develop the professional competencies that conventional teaching struggles to scale.
-
GetHelp: AI-Powered Help-Seeking in Programming Education
•
Understanding how students interact with AI tutors in introductory programming courses to improve learning outcomes.
-
SoL NUS Trial: LLM Adoption, Attitudes, and Behaviour at Scale
•
A large-scale investigation into how university students across disciplines adopt, use, and perceive Large Language Models in their academic and non-academic lives.
-
LLM-As-a-Judge Bias: Mitigating the Agreeableness Bias in LLM Judge Evaluations
•
Addressing the growing challenge in evaluating LLMs at scale by mitigating the strong positive bias in LLM-as-a-judge approaches.
-
Codaveri AI-Assisted Feedback: Augmenting Teaching Assistants with AI for CS1 Programming Feedback
•
Exploring a hybrid model where AI augments human Teaching Assistants to provide scalable, scaffolded programming feedback.
