Research map / Label-efficient and robust learning / Recognition and long-tail
Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use question-centric cognitive representations and the QIKT architecture instead of IEKT | KT prediction · ASSIST2009 | AUC: 0.7861±0.0027* -> 0.7878±0.0024 | No clear effect |
| use question-centric cognitive representations and the QIKT architecture instead of IEKT | KT prediction · Algebra2005 | AUC: 0.8416±0.0014$\bullet$ -> 0.8408±0.0007 | Hurt |
| use question-centric cognitive representations and the QIKT architecture instead of IEKT | KT prediction · NeurIPS34 | AUC: 0.8045±0.0002$\bullet$ -> 0.8044±0.0005 | No clear effect |
| add the IRT prediction layer (ablation) | QIKT · ASSIST2009, Algebra2005, NeurIPS34 | AUC: 0.7887±0.0017$\bullet$ -> 0.7878±0.0024; 0.8327±0.0005* -> 0.8408±0.0007; 0.8037±0.0004* -> 0.8044±0.0005 | Mixed |
| add the question-agnostic knowledge state module (ablation) | QIKT · ASSIST2009, Algebra2005, NeurIPS34 | AUC: 0.7813±0.0019* -> 0.7878±0.0024; 0.8365±0.0008* -> 0.8408±0.0007; 0.8048±0.0002$\bullet$ -> 0.8044±0.0005 | Mixed |
| add the question-centric problem solving module (ablation) | QIKT · ASSIST2009, Algebra2005, NeurIPS34 | AUC: 0.7822±0.0022* -> 0.7878±0.0024; 0.8345±0.0005* -> 0.8408±0.0007; 0.8037±0.0002* -> 0.8044±0.0005 | Helped |
| add both the knowledge state and problem solving modules (ablation) | QIKT · ASSIST2009, Algebra2005, NeurIPS34 | AUC: 0.7442±0.0043* -> 0.7878±0.0024; 0.7487±0.0008* -> 0.8408±0.0007; 0.8032±0.0002* -> 0.8044±0.0005 | Helped |
Closest papers by meaning
- 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)
- Predictive, scalable and interpretable knowledge tracing on structured domains (ICLR 2024 · similarity 0.85)
- Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing (AAAI 2025 · similarity 0.85)
- CK12: A Rounded K12 Knowledge Graph Based Benchmark for Chinese Holistic Cognition Evaluation (AAAI 2024 · similarity 0.84)
- Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy (AAAI 2024 · similarity 0.83)
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.