Research map / Learning theory and algorithms / Prediction and decision losses
A Bounded Ability Estimation for Computerized Adaptive Testing
Yan Zhuang, Qi Liu, GuanHao Zhao, Zhenya Huang, Weizhe Huang, Zachary Pardos, Enhong Chen, Jinze Wu, Xin Li
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 |
|---|---|---|---|
| Use BECAT instead of FSI selection | IRT · NIPS-EDU | AUC: 2.48% AUC gain | Improved |
| Use BECAT instead of FSI selection | IRT · ASSIST and EXAM | AUC: 0.32% | Improved |
| Use BECAT instead of other selection algorithms at step 20 | IRT and NeuralCDM · ASSIST | ACC@20 and AUC@20: 1.5% ACC@20, 1.1% AUC@20 | Improved |
| Use BECAT instead of BOBCAT early in the test | IRT · NIPS-EDU | ACC@5: 69.51 -> 66.98 | Hurt |
| Use BECAT instead of NCAT at step 20 | NeuralCDM · EXAM | ACC@20: 81.53 -> 84.77 | Improved |
| Use BECAT instead of FSI for simulated ability estimation | IRT · EXAM | questions needed for same MSE: up to 20% less questions | Improved |
| Use BECAT instead of FSI for simulated ability estimation | IRT · EXAM | average questions needed: 15% less questions | Improved |
| Add lazy evaluation and multifaceted estimation speedups (ablation) | BECAT · selection time | time (sec): average speedup of 3x | Improved |
| Use BECAT with speedups instead of MAAT | BECAT · selection time | time (sec): 7x | Improved |
Closest papers by meaning
- Computerized Adaptive Testing via Collaborative Ranking (NeurIPS 2024 · similarity 0.90)
- Explicit and Implicit Examinee-Question Relation Exploiting for Efficient Computerized Adaptive Testing (AAAI 2025 · similarity 0.89)
- A Unified Adaptive Testing System Enabled by Hierarchical Structure Search (ICML 2024 · similarity 0.89)
- Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks (ICML 2026 · similarity 0.82)
- AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners (NeurIPS 2025 · similarity 0.81)
- Active Test-Time Adaptation: Theoretical Analyses and An Algorithm (ICLR 2024 · similarity 0.81)
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.
