27 citations · 31 across the 14 of their papers we have counts for
15 papers
Nearly sharp stability of polynomial spectral Ritz projections
Yongxing Guo, Yuwen Li
We establish nearly sharp stability estimates for the Legendre spectral Ritz projection associated with Laplacian on a square domain. Its norm grows proportionally t…
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…
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…
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…
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…
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…
AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms
LearnLM Team, Eedi, : +33
One-to-one tutoring is widely considered the gold standard for personalized education, yet it remains prohibitively expensive to scale. To evaluate whether generative AI might help…
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…
LookAlike: Consistent Distractor Generation in Math MCQs
Nisarg Parikh, Nigel Fernandez, Alexander Scarlatos +2
Large language models (LLMs) are increasingly used to generate distractors for multiple-choice questions (MCQs), especially in domains like math education. However, existing approa…
PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues
Matthew Zent, Digory Smith, Simon Woodhead
Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-science data sharing initiatives. While PII identification has made…
DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions
Nigel Fernandez, Alexander Scarlatos, Wanyong Feng +2
High-quality distractors are crucial to both the assessment and pedagogical value of multiple-choice questions (MCQs), where manually crafting ones that anticipate knowledge defici…
Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank
Alexander Scarlatos, Wanyong Feng, Digory Smith +2
Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the d…
Math Multiple Choice Question Generation via Human-Large Language Model Collaboration
Jaewook Lee, Digory Smith, Simon Woodhead +1
Multiple choice questions (MCQs) are a popular method for evaluating students' knowledge due to their efficiency in administration and grading. Crafting high-quality math MCQs is a…
Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models
Wanyong Feng, Jaewook Lee, Hunter McNichols +5
Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable format in assessments and practices.…
Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
Alexander Scarlatos, Digory Smith, Simon Woodhead +1
Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes…