activity
20242026
collaborators

10 papers

cs.CL2026

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization

Jaewook Lee, Alexander Scarlatos, Simon Woodhead +1

With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior wo…

cs.CL2026

Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues

Zhangqi Duan, Shuyan Huang, Alexander Scarlatos +3

A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor m…

cs.CL2026

Simulated Students in Tutoring Dialogues: Substance or Illusion?

Alexander Scarlatos, Jaewook Lee, Simon Woodhead +1

Advances in large language models (LLMs) enable many new innovations in education. However, evaluating the effectiveness of new technology requires real students, which is time-con…

cs.LG2026

Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing

Joshua Mitton, Prarthana Bhattacharyya, Ralph Abboud +1

Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy. However, responsible real-world deployment requires models to know when to defer u…

cs.CL2026

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs

Prarthana Bhattacharyya, Joshua Mitton, Ralph Abboud +1

Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions. One of the key approaches to…

cs.CL2026

Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank

Joshua Mitton, Prarthana Bhattacharyya, Digory Smith +3

Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly d…