Research map / Label-efficient and robust learning / Knowledge distillation
No Task Left Behind: Multi-Task Learning of Knowledge Tracing and Option Tracing for Better Student Assessment
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 |
|---|---|---|---|
| Train KT and OT jointly with an intermediate mixing ratio rather than using either task alone (ablation) | DP-MTL · Across datasets and models | SP-MAE, KT-AUC, and OT-ACC | Helped |
| Use OT alone instead of KT alone (ablation) | DP-MTL · TOEIC | KT-AUC | Helped |
| Use DP-BiDKT rather than the first-runner-up | DP-MTL · TOEIC_Top50 | KT-AUC: +6.6% | Helped |
| Use DP-BiDKT rather than the first-runner-up | DP-MTL · TOEIC_Top50 | OT-ACC: +3.9% | Helped |
| Provide option information as input and generate separate output representations for each option, rather than using a shared position-based output layer | DP-NMF and DP-BiDKT · Multiple-choice questions | Option tracing performance | Helped |
Closest papers by meaning
- Uncertainty-aware Knowledge Tracing (AAAI 2025 · similarity 0.86)
- EduDiag: A Benchmark for Educational Diagnostic Reasoning with Error Tracing and Correction on Large Multimodal Models (CVPR 2026 · similarity 0.84)
- Neighborhood-Aware Negative Sampling for Student Knowledge and Behavior Modeling (AAAI 2025 · similarity 0.83)
- The Signal is in the Steps: Local Scoring for Reasoning Data Selection (ICML 2026 · similarity 0.83)
- Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition (AAAI 2025 · similarity 0.83)
- Automated Assessment of Student Self-Explanation in Code Comprehension Using Pre-Trained Language Models (AAAI 2025 · 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.