AI Paper Atlas

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

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use BECAT instead of FSI selectionIRT · NIPS-EDUAUC: 2.48% AUC gainImproved
Use BECAT instead of FSI selectionIRT · ASSIST and EXAMAUC: 0.32%Improved
Use BECAT instead of other selection algorithms at step 20IRT and NeuralCDM · ASSISTACC@20 and AUC@20: 1.5% ACC@20, 1.1% AUC@20Improved
Use BECAT instead of BOBCAT early in the testIRT · NIPS-EDUACC@5: 69.51 -> 66.98Hurt
Use BECAT instead of NCAT at step 20NeuralCDM · EXAMACC@20: 81.53 -> 84.77Improved
Use BECAT instead of FSI for simulated ability estimationIRT · EXAMquestions needed for same MSE: up to 20% less questionsImproved
Use BECAT instead of FSI for simulated ability estimationIRT · EXAMaverage questions needed: 15% less questionsImproved
Add lazy evaluation and multifaceted estimation speedups (ablation)BECAT · selection timetime (sec): average speedup of 3xImproved
Use BECAT with speedups instead of MAATBECAT · selection timetime (sec): 7xImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy