Research map / Reinforcement learning / Visual and representation RL
Fully Adaptive Framework: Neural Computerized Adaptive Testing for Online Education
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 NCAT instead of BOBCAT | IRT-based CAT · ASSIST, step 20 | ACC: 0.749 -> 0.756 | Helped |
| Use NCAT instead of BOBCAT | IRT-based CAT · NIPS-EDU, step 20 | ACC: 0.723 -> 0.732 | Helped |
| Use NCAT instead of MAAT | IRT-based CAT · EXAM, step 20 | ACC: 0.845 -> 0.852 | Helped |
| Add Performance Learning to Contradiction Learning (ablation) | NCAT · ASSIST, IRT, step 20 | ACC: 0.7415 -> 0.7562 | Helped |
| Add Performance Learning to Contradiction Learning (ablation) | NCAT · NIPS-EDU, IRT, step 20 | ACC: 0.7059 -> 0.7321 | Helped |
| Add Performance Learning to Contradiction Learning (ablation) | NCAT · EXAM, IRT, step 20 | ACC: 0.8351 -> 0.8516 | Helped |
| Add Contradiction Learning to Performance Learning (ablation) | NCAT · ASSIST, IRT, step 20 | ACC: 0.7508 -> 0.7562 | Helped |
| Add Contradiction Learning to Performance Learning (ablation) | NCAT · NIPS-EDU, IRT, step 20 | ACC: 0.7235 -> 0.7321 | Helped |
| Add Contradiction Learning to Performance Learning (ablation) | NCAT · EXAM, IRT, step 20 | ACC: 0.8417 -> 0.8516 | Helped |
| Set ν → 0 for deterministic selection instead of temperature-based stochastic selection (ablation) | NCAT · ASSIST, IRT, step 20 | ACC: 0.7562 -> 0.7586 | Helped |
| Set ν → 0 for deterministic selection instead of temperature-based stochastic selection (ablation) | NCAT · NIPS-EDU, IRT, step 20 | ACC: 0.7321 -> 0.7329 | Helped |
| Set ν → 0 for deterministic selection instead of temperature-based stochastic selection (ablation) | NCAT · EXAM, IRT, step 20 | ACC: 0.8516 -> 0.8530 | Helped |
Closest papers by meaning
- Explicit and Implicit Examinee-Question Relation Exploiting for Efficient Computerized Adaptive Testing (AAAI 2025 · similarity 0.90)
- Computerized Adaptive Testing via Collaborative Ranking (NeurIPS 2024 · similarity 0.88)
- A Unified Adaptive Testing System Enabled by Hierarchical Structure Search (ICML 2024 · similarity 0.86)
- Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection (ICML 2025 · similarity 0.84)
- Enhancing Question Generation through Diversity-Seeking Reinforcement Learning with Bilevel Policy Decomposition (AAAI 2025 · similarity 0.83)
- Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay (NeurIPS 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.