The paper introduces Practical Integrated Cross-consistent Knowledge Tracing (PICKT), a model that incorporates multiple feature types to improve Knowledge Tracing robustness when new questions lack interaction history. It evaluates the impact of difficulty, textual, and knowledge‑map relational features, finding that difficulty is especially informative for hard questions, while fused text and map features help estimate unseen questions by leveraging similar ones seen during training. The study concludes that prioritizing feature annotation aligned with educational service characteristics is essential for maintaining robust diagnostics in Intelligent Tutoring Systems.
By Wonbeen Lee, Channyoung Lee, Junho Sohn, Hansam Cho
The paper introduces Process-aware Language Cognitive Diagnosis (PLCD), a framework that replaces traditional ID-based embeddings in Cognitive Diagnosis Models with language-derived structures and response records. PLCD employs large language models to build concept schemas and cognitive process graphs, and uses a Language-to-Cognition Mapper with DA-MoE experts and contrastive learning to map textual evidence into a unified cognitive space. Experiments demonstrate that PLCD outperforms conventional baselines in student performance prediction and shows strong cognitive transfer, improving cold-start robustness and cognitive grounding.
By Minghang Liu, Yuanzhuo Wang, Qiang Qiu, Huawei Shen, Xueqi Cheng
arXiv:2509. 22888v2 Announce Type: replace Abstract: Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature.
By Louie Hong Yao, Nicholas Jarvis, Tiffany Zhan, Saptarshi Ghosh, Linfeng Liu, Tianyu Jiang
The paper introduces LT‑MKT, a new method for multi‑domain knowledge tracing that incorporates cognitive load and knowledge transfer. It constructs a multi‑domain hierarchical graph using textual information from questions and concepts, then explicitly models cross‑domain temporal and knowledge features to capture cognitive load effects. A knowledge transfer module further captures propagation of knowledge states within and across domains, leading to more accurate predictions of students’ future performance.
By Haotian Zhang, Shucun Wang, Jinze Wu, Liang Ding, Shuochen Liu, Zhenya Huang, Jing Sha, Shijin Wang, Qi Liu
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
arXiv:2606. 28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction.
By Chenguang Wang, Ming Li, Xinyue Zeng, Zhuochun Li, Hong Jiao, Tianyi Zhou, Dawei Zhou
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
EduAgentQG is a multi‑agent framework for generating personalized mathematics questions that explicitly controls diversity and aligns with educational objectives. It operates through a closed‑loop cycle of planning, writing, evaluation, refinement, and checking, using fine‑grained evaluation to ensure logical correctness, solvability, and alignment with knowledge concepts, difficulty, grade level, and core competencies. The authors built a benchmark of 10,273 questions across Grades 1‑9 and demonstrated that EduAgentQG outperforms existing methods in diversity, objective consistency, and win rate.
By Rui Jia, Min Zhang, Fengrui Liu, Bo Jiang, Kun Kuang, Zhongxiang Dai
arXiv:2609.15292v1 Announce Type: new
Abstract: Automatic Item Generation (AIG) is pivotal for personalized education, yet guaranteeing the pedagogical value of generated items remains a bottleneck....
By Junkai Tong, Mingjia Li, Haoran Chen, Yaoyu Jiang, Hanjie Ge, Yixuan Wang, Hong Qian
IDEAlign introduces a new protocol for evaluating the similarity of large language model (LLM) annotations to expert judgments. It uses pick‑the‑odd‑one‑out tasks to capture expert similarity and benchmarks various similarity methods—including text embeddings, topic models, and LLM-as-a-judge—against these human ratings. Applied to educational datasets, the study finds that most metrics miss nuanced expert dimensions, with LLM-as-a-judge performing best yet still insufficient for full expert alignment.
By Hyunji Nam, Lucia Langlois, James Malamut, Mei Tan, Dorottya Demszky
arXiv:2607. 26063v1 Announce Type: cross Abstract: Personalised learning systems often assume that mathematical ability is combined of discrete abilities, acquired sequentially and dependent upon first acquiring foundational abilities, and students often report different strengths.
By Benjamin Mawdsley, Tom Quilter, Richard Turner, Sarah Jackson, Paul Edwards