A Review of Data Mining in Personalized Education: Current Trends and Future Prospects

Z Xiong, H Li, Z Liu, Z Chen, H Zhou, W Rong… - arXiv preprint arXiv …, 2024 - arxiv.org
Personalized education, tailored to individual student needs, leverages educational
technology and artificial intelligence (AI) in the digital age to enhance learning effectiveness …

A survey of knowledge tracing: Models, variants, and applications

S Shen, Q Liu, Z Huang, Y Zheng, M Yin… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Modern online education has the capacity to provide intelligent educational services by
automatically analyzing substantial amounts of student behavioral data. Knowledge Tracing …

Improving the validity of automatically generated feedback via reinforcement learning

A Scarlatos, D Smith, S Woodhead, A Lan - International Conference on …, 2024 - Springer
Automatically generating feedback via large language models (LLMs) in intelligent tutoring
systems and online learning platforms has the potential to improve the learning outcomes of …

Algebra error classification with large language models

H McNichols, M Zhang, A Lan - International Conference on Artificial …, 2023 - Springer
Automated feedback as students answer open-ended math questions has significant
potential in improving learning outcomes at large scale. A key part of automated feedback …

Tree-based representation and generation of natural and mathematical language

A Scarlatos, A Lan - arXiv preprint arXiv:2302.07974, 2023 - arxiv.org
Mathematical language in scientific communications and educational scenarios is important
yet relatively understudied compared to natural languages. Recent works on mathematical …

Code soliloquies for accurate calculations in large language models

S Sonkar, X Chen, M Le, N Liu, D Basu Mallick… - Proceedings of the 14th …, 2024 - dl.acm.org
High-quality conversational datasets are crucial for the successful development of Intelligent
Tutoring Systems (ITS) that utilize a Large Language Model (LLM) backend. Synthetic …

Exploring automated distractor generation for math multiple-choice questions via large language models

W Feng, J Lee, H McNichols, A Scarlatos… - arXiv preprint arXiv …, 2024 - arxiv.org
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. One …

Navigating the Landscape of Hint Generation Research: From the Past to the Future

A Jangra, J Mozafari, A Jatowt, S Muresan - arXiv preprint arXiv …, 2024 - arxiv.org
Digital education has gained popularity in the last decade, especially after the COVID-19
pandemic. With the improving capabilities of large language models to reason and …

Improving socratic question generation using data augmentation and preference optimization

NA Kumar, A Lan - arXiv preprint arXiv:2403.00199, 2024 - arxiv.org
The Socratic method is a way of guiding students toward solving a problem independently
without directly revealing the solution to the problem. Although this method has been shown …

Explainable few-shot knowledge tracing

H Li, J Yu, Y Ouyang, Z Liu, W Rong, J Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Knowledge tracing (KT), aiming to mine students' mastery of knowledge by their exercise
records and predict their performance on future test questions, is a critical task in …