12 papers
The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions
Moiz Imran, Sahan Bulathwela
Automated feedback systems that rely on answer correctness will reinforce, rather than address, misconceptions when students reach the correct answer through flawed reasoning. We i…
Tool Calling is Linearly Readable and Steerable in Language Models
Zekun Wu, Ze Wang, Seonglae Cho +4
When a tool-calling agent picks the wrong tool, the failure is invisible until execution: the email gets sent, the meeting gets missed. As agents take on consequential actions, one…
Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning
Moiz Imran, Sahan Bulathwela
Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure m…
Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation
Nathikan Yodthapa, Thanapong Intharah, Sahan Bulathwela
Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augmentation strategy for trainin…
Gaze to Insight: A Scalable AI Approach for Detecting Gaze Behaviours in Face-to-Face Collaborative Learning
Junyuan Liang, Qi Zhou, Sahan Bulathwela +1
Previous studies have illustrated the potential of analysing gaze behaviours in collaborative learning to provide educationally meaningful information for students to reflect on th…
Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
Max Norris, Kobi Gal, Sahan Bulathwela
Modelling student knowledge is a key challenge when leveraging AI in education, with major implications for personalised learning. The Knowledge Tracing (KT) task aims to predict h…