The paper introduces an interpretable, difficulty-aware knowledge tracing framework for tutor‑student dialogues that leverages large language models. It explicitly models student ability and question difficulty at each turn, using the original question text and the next tutor‑posed task to estimate knowledge state. By integrating Item Response Theory, the framework translates LLM outputs into cognitive‑theory‑based parameters, achieving superior performance over existing baselines while producing interpretable predictions.
By Shuyan Huang, Alexander Scarlatos, Jaewook Lee, Andrew Lan
The paper introduces Knowledge Tracing Leveraging Problem‑Solving Process (KT‑PSP), a method that incorporates students’ problem‑solving steps to model mathematical proficiency more comprehensively than traditional knowledge tracing. It presents the KT‑PSP‑25 dataset and a new framework, StatusKT, which uses a teacher‑student‑teacher LLM pipeline to extract proficiency indicators, generate responses, and evaluate mastery. Experiments show that StatusKT improves prediction accuracy and offers interpretable explanations by explicitly modeling proficiency.
By Jungyang Park, Suho Kang, Jaewoo Park, Jaehong Kim, Jaewoo Shin, Seonjoon Park, Youngjae Yu
arXiv:2509.05346v3 Announce Type: replace
Abstract: While large language models (LLMs) are increasingly being adopted to support personalized learning, there remains limited understanding of how thei...
By Bo Yuan, Jiazi Hu
The paper explores using semantic text embeddings to automatically build educational taxonomies by clustering math question embeddings. It compares these embedding‑based taxonomies to existing Common Core State Standards (CCSS) taxonomies in two ASSISTments datasets, finding substantial but incomplete overlap. When applied to Deep Knowledge Tracing, the new taxonomies improve predictive performance by about 3‑5 AUC percentage points.
By Kia Karbasi, Kaveh Karbasi, Gregory Pottie
arXiv:2610.19532v1 Announce Type: cross
Abstract: Existing student models in educational applications largely focus on student responses to questions. However, as tutoring becomes more accessible at...
By Zhangqi Duan, Simon Woodhead, Maya Miller-Vedam, Andrew Lan
The paper introduces TIZSKT, a zero‑shot cross‑domain knowledge tracing model that separates behavioral sequence modeling from domain‑local historical evidence construction. It uses text as an index via a frozen text encoder and unsupervised per‑domain projection to build question addresses, then aggregates a student’s past outcomes into a question‑specific historical correctness summary. Experiments on three public datasets show that TIZSKT outperforms baselines in mean AUC and accuracy, with ablations confirming the importance of text addressing and cross‑segment continuation.
By Yin Yi, Haiping Ma, Siyu Song, Ziwen Wang, Shangshang Yang
arXiv:2610.08703v1 Announce Type: new
Abstract: In K-12 mathematics tutoring, student-tutor dialogue provides rich evidence of learners' problem-solving processes and sources of difficulty. Learning...
By Clayton Cohn, Joyce Fonteles, Kirk Vanacore, Gianni Mazza, Candida Crawford, Tom Hooper, Gautam Biswas, Rene Kizilcec
arXiv:2606. 10736v1 Announce Type: cross Abstract: Large online courses generate thousands of student questions directed at conversational AI teaching assistants, yet these interaction logs remain largely untapped as diagnostic signals.
By Youssef Medhat, Junsoo Park, Ploy Thajchayapong, Ashok K. Goel
arXiv:2606. 12767v1 Announce Type: new Abstract: Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system is expected to use.
By Sarah Elshabrawy, Rahul K. Dass, Ashok K. Goel
arXiv:2610.35609v1 Announce Type: cross
Abstract: Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/w...
By Trystan Geoffre, Zheng Yuan, Thierry Geoffre
arXiv:2603. 02830v2 Announce Type: replace-cross Abstract: Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions.
By Prarthana Bhattacharyya, Joshua Mitton, Ralph Abboud, Simon Woodhead
The paper investigates how language models acquire knowledge over the course of pretraining by using point-in-time models trained on web snapshots from different years. It introduces a temporal variability score (TVS) that measures how consistently a knowledge item is represented across these snapshots. The study finds that items with high TVS improve more rapidly later in training and outperform low‑TVS items in most benchmark settings, especially on knowledge‑intensive tasks.
By Chang Su, Bin Wu, Emine Yilmaz, Yao Lu