Research map / Large language models / Retrieval and knowledge
Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
Xingcheng Fu, Shengpeng Wang, Yisen Gao, Xianxian Li, Chunpei Li, Qingyun Sun, Dongran Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hyperbolic representation learning (vs Euclidean) (ablation) | L-HAKT · ASSIST09 | AUC (%): 77.55 -> 80.22 | Improved |
| add multi-level contrastive alignment (ablation) | L-HAKT · ASSIST09 | AUC (%): 76.98 -> 80.22 | Improved |
| add hyperbolic representation learning (vs Euclidean) (ablation) | L-HAKT · ASSIST12 | AUC (%): 78.01 -> 80.27 | Improved |
| add multi-level contrastive alignment (ablation) | L-HAKT · ASSIST12 | AUC (%): 76.32 -> 80.27 | Improved |
| add hyperbolic representation learning (vs Euclidean) (ablation) | L-HAKT · EdNet | AUC (%): 76.54 -> 78.23 | Improved |
| add multi-level contrastive alignment (ablation) | L-HAKT · EdNet | AUC (%): 75.51 -> 78.23 | Improved |
| add hyperbolic representation learning (vs Euclidean) (ablation) | L-HAKT · Eedi | AUC (%): 79.02 -> 80.29 | Improved |
| add multi-level contrastive alignment (ablation) | L-HAKT · Eedi | AUC (%): 78.19 -> 80.29 | Improved |
| add hyperbolic representation learning (ablation) | L-HAKT · ASSIST09 | ACC (%): 73.78 -> 75.10 | Improved |
| add contrastive alignment (ablation) | L-HAKT · ASSIST09 | ACC (%): 73.21 -> 75.10 | Improved |
| add LLM-student hyperbolic alignment framework to GKT backbone | GKT · ASSIST12 | AUC (%): 72.39 -> 80.27 | Improved |
| add LLM-student hyperbolic alignment framework to GKT backbone | GKT · EdNet | AUC (%): 69.21 -> 78.23 | Improved |
Closest papers by meaning
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.87)
- K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs (NeurIPS 2026 · similarity 0.86)
- Extended LSTMs for Knowledge Tracing: Peeking Inside the Black Box (Student Abstract) (AAAI 2025 · similarity 0.86)
- Uncertainty-aware Knowledge Tracing (AAAI 2025 · similarity 0.86)
- Knowledge Is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis (AAAI 2025 · similarity 0.85)
- Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing Models (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
