Survey of Computerized Adaptive Testing: A Machine Learning Perspective
Open accessAbstract
Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual performance. Compared to traditional, non-personalized testing methods, CAT requires fewer questions and provides more accurate assessments. As a result, CAT has been widely adopted across various fields, including education, healthcare, sports, sociology, and the evaluation of AI models. While traditional methods rely on psychometrics and statistics, the increasing complexity of large-scale testing has spurred the integration of machine learning techniques. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing paradigm. We delve into measurement models, question selection algorithm, bank construction, and test control within CAT, exploring how machine learning can optimize these components. Through an analysis of current methods, strengths, limitations, and challenges, we strive to develop robust, fair, and efficient CAT systems. By bridging psychometric-driven CAT research with machine learning, this survey advocates for a more inclusive and interdisciplinary approach to the future of adaptive testing.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Item parameters estimated from LLM responses highly correlated with those from expert predictions (Spearman's > 0.8).
“Another study found that item parameters estimated from LLM responses highly correlated with those from expert predictions (Spearman’s > 0.8)17.”
From Leveraging computerized adaptive testing for cost-effective evaluation of large language models in medical benchmarking (2026) · cites this paper as [17]
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 2× · see citing works
“Reinforcement learning (RL), a subfield of machine learning, is a powerful approach that enables an agent to learn how to make optimal decisions automatically [135].”
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217 · cited 1× · see citing works
“Thus, the binary classificationmetricscanbeusedforevaluations,e.g.,Prediction Accuracy(ACC)andAreaUnderROCCurve(AUC)[182].”
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812 · cited 1× · see citing works
“The assessment of intelligent agents, whether human or AI systems, is essential for ensuring that individuals are well-prepared to meet the demands of their respective roles [1], [2].”
Applications of Item Response Theory To Practical Testing Problems
Lord, F. M. (2012) · Routledge eBooks · doi:10.4324/9780203056615 · Cited by 5,009 · cited 4× · see citing works
“For example, the Maximum Fisher Information tends to select questions with high discrimination [14].”
InfluentialDeep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733 · cited 1× · see citing works
“It has been successfully applied in various domains, including robotics, autonomous vehicles, education, and healthcare [136], [137].”
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · cited 1× · see citing works
“Various large-scale benchmarks and their corresponding response data can be utilized to build and test CAT systems, such as Google’s BIG-bench [187], HuggingFace’s Open LLM Leader-board [188], HELM [189], and AlpacaEval [190].”
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 2,842 · cited 1× · see citing works
“Empowering CAT with Generative AI: Generative artificial intelligence (e.g., LLMs) is trained on massive, cross-domain datasets, endowing it with versatility and a profound repository of world knowledge [193], [194].”
Gulliksen, H. O. (1950) · John Wiley & Sons, Inc. eBooks · doi:10.1037/13240-000 · Cited by 2,184 · see citing works
Multi-objective Optimisation Using Evolutionary Algorithms: An Introduction
Deb, K. (2011) · Springer eBooks · doi:10.1007/978-0-85729-652-8_1 · Cited by 1,003 · cited 1× · see citing works
“At each step, it uses multi-objective evolutionary algorithms to obtain the set of Pareto-optimal solutions [151] by maximizing precision and minimizing the number of questions.”
Subset Selection in Regression
Miller, A. (2002) · Chapman & Hall/CRC eBooks · doi:10.1201/9781420035933 · Cited by 941 · see citing works
Fisher information and stochastic complexity
Rissanen, J. J. (1996) · IEEE Transactions on Information Theory · doi:10.1109/18.481776 · Cited by 814 · cited 1× · see citing works
“Fisher Information: In the parameter estimation problems, Fisher Information [122] is a concept from information theory and statistics that measures the amount of information that an observable random variable carries about the unknown parameter.”
Embretson, S. E., & Reise, S. P. (2013) · Psychology Press eBooks · doi:10.4324/9781410605269 · Cited by 798 · see citing works
The Generalized DINA Model Framework
TORRE, J. D. L. (2011) · Psychometrika · doi:10.1007/s11336-011-9207-7 · Cited by 787 · cited 2× · see citing works
“In recent years, the rapid growth of deep learning techniques stimulates the development of deep learning-driven Measurement Models.”
Baker, F. B., & Kim, S.-H. (2004) · CRC Press eBooks · doi:10.1201/9781482276725 · Cited by 746 · see citing works
Learning Loss for Active Learning
Yoo, D., & Kweon, I. S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00018 · Cited by 740 · see citing works
DINA Model and Parameter Estimation: A Didactic
TORRE, J. D. L. (2008) · Journal of Educational and Behavioral Statistics · doi:10.3102/1076998607309474 · Cited by 675 · cited 3× · see citing works
“It doesn’t assign a selected question to the examinee immediately; instead, it passes through a probability filter.”
Wainer, H., Dorans, N. J., Flaugher, R. L., Green, B. F., & Mislevy, R. J. (2000) · Routledge eBooks · doi:10.4324/9781410605931 · Cited by 659 · cited 1× · see citing works
“Here, d represents the proficiency’s dimension; for example, θ may correspond to a unidimensional overall ability level ( d = 1 ) or a multidimensional vector representing mastery levels across d distinct knowledge concepts.”
TEST BIAS: PREDICTION OF GRADES OF NEGRO AND WHITE STUDENTS IN INTEGRATED COLLEGES
Cleary, T. A. (1968) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.1968.tb00613.x · Cited by 658 · see citing works
Item Clusters and Computerized Adaptive Testing: A Case for Testlets
Wainer, H., & Kiely, G. L. (1987) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.1987.tb00274.x · Cited by 634 · cited 1× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
18 Multidimensional Item Response Theory
Reckase, M. D. (2006) · Handbook of statistics · doi:10.1016/s0169-7161(06)26018-8 · Cited by 582 · see citing works
Item bias and item response theory
Mellenbergh, G. J. (1989) · International Journal of Educational Research · doi:10.1016/0883-0355(89)90002-5 · Cited by 553 · cited 1× · see citing works
“Variousmethods havebeenproposedtodetectthistypeofbias[109],[110], [111].”
van der Linden, W. J., & van der Linden, W. J. (2010) · Springer eBooks · doi:10.1007/978-0-387-85461-8 · Cited by 515 · see citing works
Addressing the assessment challenge with an online system that tutors as it assesses
Feng, M., Heffernan, N. T., & Koedinger, K. R. (2009) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-009-9063-7 · Cited by 508 · see citing works
An Analysis of Stochastic Shortest Path Problems
Bertsekas, D. P., & Tsitsiklis, J. N. (1991) · Mathematics of Operations Research · doi:10.1287/moor.16.3.580 · Cited by 502 · cited 1× · see citing works
“These datasets are useful for validating the CAT system’s capability to estimate proficiencies accurately and to adapt to the simulated changes during the testing process.”
Holistic Evaluation of Language Models
Bommasani, R., Liang, P., & Lee, T. (2023) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.15007 · Cited by 480 · see citing works
DeVellis, R. F. (2006) · Medical Care · doi:10.1097/01.mlr.0000245426.10853.30 · Cited by 476 · cited 1× · see citing works
“In Classic Test Theory, question difficulty is calculated as the proportion of correct responses within exam-inees [82], [156], while discrimination is derived from performance disparities between higher and lower ability exami-nees [83].”
Active Learning by Querying Informative and Representative Examples
Huang, S.-J., Jin, R., & Zhou, Z. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2307881 · Cited by 441 · cited 1× · see citing works
“This technique has improved data efficiency in numerous learning tasks [130].”
Leighton, J. P., Gierl, M. J., & Hunka, S. M. (2004) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.2004.tb01163.x · Cited by 393 · cited 1× · see citing works
“Another approach, the Attribute Hierarchy Method [51], applies rule space theory to structure knowledge dependencies and align examinee proficiencies with the nearest ideal cognitive patterns to obtain diagnostic results.”
TECHNICAL GUIDELINES FOR ASSESSING COMPUTERIZED ADAPTIVE TESTS
Green, B. F., Bock, R. D., Humphreys, L. G., Linn, R. L., & Reckase, M. D. (1984) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.1984.tb01039.x · Cited by 386 · see citing works
A Global Information Approach to Computerized Adaptive Testing
Chang, H., & Ying, Z. (1996) · Applied Psychological Measurement · doi:10.1177/014662169602000303 · Cited by 369 · cited 3× · see citing works
“To address this issue, Chang et al. [15] proposed a global information measure based on Kullback–Leibler (KL) divergence.”
Algorithmic fairness in education
Kizilcec, R. F., & Lee, H. (2022) · Routledge eBooks · doi:10.4324/9780429329067-10 · Cited by 302 · see citing works
A primer on classical test theory and item response theory for assessments in medical education
Champlain, A. F. D. (2009) · Medical Education · doi:10.1111/j.1365-2923.2009.03425.x · Cited by 297 · cited 1× · see citing works
“It is resource-intensive nature and involves pre-testing with exam-inees [155].”
a-Stratified Multistage Computerized Adaptive Testing
Chang, H., & Ying, Z. (1999) · Applied Psychological Measurement · doi:10.1177/01466219922031338 · Cited by 293 · see citing works
Learning Tree-based Deep Model for Recommender Systems
Han, Z., Li, X., Zhang, P., Li, G., He, J., Li, H., & Gai, K. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3219826 · Cited by 292 · see citing works
Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
Rong, Y., Leemann, T., Nguyen, T.-T., Fiedler, L., Qian, P., Unhelkar, V., Seidel, T., Kasneci, G., & Kasneci, E. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3331846 · Cited by 278 · cited 1× · see citing works
“The assessment of intelligent agents, whether human or AI systems, is essential for ensuring that individuals are well-prepared to meet the demands of their respective roles [1], [2].”
Benchmarking Adversarial Robustness on Image Classification
Dong, Y., Fu, Q.-A., Yang, X. F., Pang, T., Su, H., Xiao, Z., & Zhu, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00040 · Cited by 275 · see citing works
EdNet: A Large-Scale Hierarchical Dataset in Education
Choi, Y., Lee, Y., Shin, D., Cho, J., Park, S., Lee, S., Baek, J., Bae, C., Kim, B., & Heo, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-52240-7_13 · Cited by 273 · cited 1× · see citing works
“It includes a range of publicly available datasets along with previously private datasets, e.g., ASSIST-ments [183], Junyi [184], EdNet [185], and Eedi2020 [186].”
Computerized adaptive testing: From inquiry to operation.
(1997) · American Psychological Association eBooks · doi:10.1037/10244-000 · Cited by 232 · cited 1× · see citing works
“The primary goal of CAT is to accurately and efficiently estimate examinees’ true proficiency levels by having them answer questions.”
Psychometrics Behind Computerized Adaptive Testing
Chang, H. (2014) · Psychometrika · doi:10.1007/s11336-014-9401-5 · Cited by 206 · cited 1× · see citing works
“The goal of CAT is to find a question set S = { q 1 , q 2 , ..., q T } of size T , such that the final step estimate ˆ θ T , derived from S and their corresponding response labels y , closely approximates the examinee’s true proficiency θ 0 : However, solving this optimization problem directly is…”
Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests
Ackerman, T. A., Gierl, M. J., & Walker, C. M. (2003) · Educational Measurement Issues and Practice · doi:10.1111/j.1745-3992.2003.tb00136.x · Cited by 197 · see citing works
Data Analytic Methods for Latent Partially Ordered Classification Models
Tatsuoka, C. M. (2002) · Journal of the Royal Statistical Society Series C (Applied Statistics) · doi:10.1111/1467-9876.00272 · Cited by 188 · cited 2× · see citing works
“To design selection algorithms that are effective across different measurement models i.e., model-agnostic , researchers explore a general machine learning technique for data selection: Active Learning [129].”
A Model and Heuristic For Solving Very Large Item Selection Problems
Swanson, L., & Stocking, M. L. (1993) · Applied Psychological Measurement · doi:10.1177/014662169301700205 · Cited by 181 · cited 2× · see citing works
“The Weighted Deviation Model [98] manages the degree of overlap, maintaining rep-resentativeness and preventing question overexposure.”
RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems
Gao, W., Liu, Q., Huang, Z., Yin, Y., Bi, H., Wang, M., Ma, J., Wang, S., & Su, Y. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462932 · Cited by 180 · see citing works
Self-citationWhen Cognitive Diagnosis Meets Computerized Adaptive Testing: CD-CAT
Cheng, Y. (2009) · Psychometrika · doi:10.1007/s11336-009-9123-2 · Cited by 177 · cited 3× · see citing works
“Itwasnotuntil2009,withtheintroductionofCD-CAT[64],that CDMbegantobeusedastheunderlyingmeasurementmodel inadaptivetesting.”
InfluentialFuzzy Cognitive Diagnosis for Modelling Examinee Performance
Liu, Q., Wu, R., Chen, E., Xu, G., Su, Y., Chen, Z., & Hu, G. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3168361 · Cited by 177 · cited 1× · see citing works
“Its extension G-DINA [50] provides a granular view of examinee proficiency, while FuzzyCDF [52] leverages fuzzy set theory for nuanced diagnostics from both objective and subjective data.”
Self-citationBayesian Item Selection Criteria for Adaptive Testing
van der Linden, W. J. (1998) · Psychometrika · doi:10.1007/bf02294775 · Cited by 171 · cited 2× · see citing works
“Maximum Expected Information [62] accounts for all possible outcomes y t and their impact on the updated proficiency estimate when weighting Fisher information.”
NeuralCD: A General Framework for Cognitive Diagnosis
Wang, F., Liu, Q., Chen, E., Huang, Z., Yin, Y., Wang, S., & Su, Y. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3201037 · Cited by 168 · cited 2× · see citing works
“For example, deep learning techniques diagnose examinee’s proficiency [22] and automate question bank construction [23]; data-driven approaches optimize selection algorithms by learning from large-scale response data [24], [25], [26].”
Self-citationA Comparison of Item Exposure Control Methods in Computerized Adaptive Testing
Revuelta, J., & Ponsoda, V. (1998) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.1998.tb00541.x · Cited by 166 · see citing works
Some Practical Examples of Computer‐Adaptive Sequential Testing
Luecht, R. M., & Nungester, R. J. (1998) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.1998.tb00537.x · Cited by 164 · cited 2× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
Regularizing Deep Networks with Semantic Data Augmentation
Wang, Y., Huang, G. M., Song, S., Pan, X., Xia, Y., & Wu, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3052951 · Cited by 164 · see citing works
Test Construction for Cognitive Diagnosis
Henson, R. A., & Douglas, J. (2005) · Applied Psychological Measurement · doi:10.1177/0146621604272623 · Cited by 159 · see citing works
Computerized Adaptive Diagnosis and Testing of Mental Health Disorders
Gibbons, R. D., Weiss, D. J., Frank, E., & Kupfer, D. J. (2015) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-021815-093634 · Cited by 159 · see citing works
Hierarchical Multi-label Text Classification
Huang, W., Chen, E., Liu, Q., Chen, Y., Huang, Z., Liu, Y., Zhao, Z., Zhang, D., & Wang, S. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357885 · Cited by 139 · see citing works
Self-citationa-Stratified Multistage Computerized Adaptive Testing with b Blocking
Chang, H., Qian, J., & Ying, Z. (2001) · Applied Psychological Measurement · doi:10.1177/01466210122032181 · Cited by 129 · see citing works
Some New Item Selection Criteria for Adaptive Testing
Veerkamp, W. J. J., & Berger, M. P. F. (1997) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986022002203 · Cited by 122 · cited 1× · see citing works
“The Maximum Likelihood Weighted Information [125] weights the Fisher information by the likelihood function of the exam-inee’s current response results.”
An adaptive testing system for supporting versatile educational assessment
Huang, Y., Lin, Y.-T., & Cheng, S.-C. (2008) · Computers & Education · doi:10.1016/j.compedu.2008.06.007 · Cited by 121 · see citing works
Question Difficulty Prediction for READING Problems in Standard Tests
Huang, Z., Liu, Q., Chen, E., Zhao, H., Gao, M., Wei, S., Su, Y., & Hu, G. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10740 · Cited by 118 · see citing works
Self-citationRecommendation System for Adaptive Learning
Chen, Y., Li, X., Liu, J., & Ying, Z. (2017) · Applied Psychological Measurement · doi:10.1177/0146621617697959 · Cited by 113 · cited 2× · see citing works
“Reinforcement learning (RL), a subfield of machine learning, is a powerful approach that enables an agent to learn how to make optimal decisions automatically [135].”
Constraining Item Exposure in Computerized Adaptive Testing With Shadow Tests
van der Linden, W. J., & Veldkamp, B. P. (2004) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986029003273 · Cited by 107 · see citing works
Gibbons, R. D., Hooker, G., Finkelman, M. D., Weiss, D. J., Pilkonis, P. A., Frank, E., Moore, T., & Kupfer, D. J. (2013) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.12m08338 · Cited by 101 · see citing works
Item response theory in AI: Analysing machine learning classifiers at the instance level
Martínez‐Plumed, F., Prudêncio, R. B. C., Martínez-Usó, A., & Hernández‐Orallo, J. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.09.004 · Cited by 101 · cited 1× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
The DINA model as a constrained general diagnostic model: Two variants of a model equivalency
von Davier, M. (2013) · British Journal of Mathematical and Statistical Psychology · doi:10.1111/bmsp.12003 · Cited by 97 · cited 2× · see citing works
“It doesn’t assign a selected question to the examinee immediately; instead, it passes through a probability filter.”
Cheng, S., Liu, Q., Chen, E., Huang, Z., Huang, Z., Chen, Y., Ma, H., & Hu, G. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358070 · Cited by 95 · cited 1× · see citing works
“For example, DIRT [53] uses a neural network to capture semantic information from question texts to empower accuracy.”
Self-citationTheory of self-learning $Q$-matrix
Liu, J., Xu, G., & Ying, Z. (2013) · Bernoulli · doi:10.3150/12-bej430 · Cited by 86 · see citing works
Deep Reinforcement Learning for Adaptive Learning Systems
Li, X., Xu, H., Zhang, J., & Chang, H. (2022) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986221129847 · Cited by 83 · see citing works
Towards Next-Generation Intelligent Assistants Leveraging LLM Techniques
Dong, X. L., Moon, S., Xu, Y. E., Malik, K., & Yu, Z. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599572 · Cited by 77 · see citing works
Comparability of Conventional and Computerized Tests of Reading in a Second Language
Sawaki, Y. (2001) · Language learning & technology · doi:10.64152/10125/25127 · Cited by 74 · see citing works
Segall, D. O. (2005) · Encyclopedia of Social Measurement · doi:10.1016/b0-12-369398-5/00444-8 · Cited by 70 · see citing works
Xu, S., Hua, W., & Zhang, Y. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657883 · Cited by 67 · cited 1× · see citing works
“These models have already shown preliminary progress in user modeling, such as recommendation systems, and in the generation of personalized strategy [195], [196].”
Development of a Computerized Adaptive Test Suicide Scale—The CAT-SS
Gibbons, R. D., Kupfer, D., Frank, E., Moore, T., Beiser, D. G., & Boudreaux, E. D. (2017) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.16m10922 · Cited by 65 · see citing works
Deep cognitive diagnosis model for predicting students’ performance
Gao, L., Zhao, Z., Li, C., Zhao, J., & Zeng, Q. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.08.019 · Cited by 63 · see citing works
Fully Adaptive Framework: Neural Computerized Adaptive Testing for Online Education
Zhuang, Y., Liu, Q., Huang, Z., Li, Z., Shen, S., & Ma, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i4.20399 · Cited by 62 · see citing works
Self-citationBuilding an Evaluation Scale using Item Response Theory
Lalor, J., Wu, H., & yu, H. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1062 · Cited by 60 · cited 2× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
Implementing the Graduate Management Admission Test Computerized Adaptive Test
Rudner, L. M. (2009) · Springer eBooks · doi:10.1007/978-0-387-85461-8_8 · Cited by 59 · cited 1× · see citing works
“To mitigate this, some organizations like GMAT [176] rely on manual filtering rules crafted by experts, which is labor-intensive and lacks scalability.”
a ‐Stratified CAT design with content blocking
Yi, Q., & Chang, H. (2003) · British Journal of Mathematical and Statistical Psychology · doi:10.1348/000711003770480084 · Cited by 52 · see citing works
Conditional Item-Exposure Control in Adaptive Testing Using Item-Ineligibility Probabilities
van der Linden, W. J., & Veldkamp, B. P. (2007) · Journal of Educational and Behavioral Statistics · doi:10.3102/1076998606298044 · Cited by 52 · cited 1× · see citing works
“Enhancements to this method have been developed to address these limitations [100], [101], [102]; (2) A-Stratified Method and its subsequent re-searches [63], [104], [106] are designed to counteract selection biases of algorithms favoring certain questions (e.g., Fisher Information prefers highly…”
Quality Meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing
Bi, H., Ma, H., Huang, Z., Yin, Y., Liu, Q., Chen, E., Su, Y., & Wang, S. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00013 · Cited by 52 · see citing works
Self-citationA Review of Recent Advances in Adaptive Assessment
Vie, J.-J., Popineau, F., Bruillard, É., & Bourda, Y. (2017) · Studies in systems, decision and control · doi:10.1007/978-3-319-52977-6_4 · Cited by 50 · cited 3× · see citing works
“Previous CAT surveys [4], [17], [18], [19] have primarily focused on statistical and psychometric perspectives, concentrating mainly on human assessments.”
Leveraging LLM respondents for item evaluation: A psychometric analysis
Liu, Y., Bhandari, S., & Pardos, Z. A. (2025) · British Journal of Educational Technology · doi:10.1111/bjet.13570 · Cited by 49 · see citing works
Self-citationData Shapley Valuation for Efficient Batch Active Learning
Ghorbani, A., Zou, J. Y., & Esteva, A. (2021) · Asilomar Conference on Signals, Systems and Computers · doi:10.1109/ieeeconf56349.2022.10064696 · Cited by 48 · see citing works
Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning
Doshi‐Velez, F., Pfau, D., Wood, F., & Roy, N. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.191 · Cited by 47 · see citing works
Lee, C.-S., Wang, M., Wang, C.-S., Teytaud, O., Liu, J., Lin, S., & Hung, P. (2018) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2018.2810814 · Cited by 47 · cited 1× · see citing works
“Recent research has explored two main directions to improve efficiency: (cid:2) Heuristic Search via PSO: Particle Swarm Optimization (PSO)hasbeenappliedinIRT-basedadaptivetesting[118], [177].”
Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards?
Rodriguez, P., Barrow, J., Hoyle, A. M., Lalor, J. P., Jia, R., & Boyd-Graber, J. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.346 · Cited by 47 · cited 2× · see citing works
“Moreover, these benchmarks are often plagued by low-quality questions, errors, and contamination issues [40].”
Task Contamination: Language Models May Not Be Few-Shot Anymore
Li, C., & Flanigan, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29808 · Cited by 47 · see citing works
Self-Supervised Graph Learning for Long-Tailed Cognitive Diagnosis
Wang, S., Zeng, Z., Yang, X., & Zhang, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25082 · Cited by 46 · see citing works
Self-citationParadoxical Results in Multidimensional Item Response Theory
Hooker, G., Finkelman, M., & Schwartzman, A. (2009) · Psychometrika · doi:10.1007/s11336-009-9111-6 · Cited by 45 · cited 1× · see citing works
“In the Appendix, (onlineavailable)weshowtheunderlyingcausesandadvantages ofdifferentfactorsinCATtestcontrol.”
Optimal Design of Item Banks for Computerized Adaptive Tests
Stocking, M. L., & Swanson, L. (1998) · Applied Psychological Measurement · doi:10.1177/01466216980223007 · Cited by 44 · cited 1× · see citing works
“Question Bank Rotating: Rotating the question bank involves dividing a master bank into smaller banks with overlapping elements, ensuring balanced exposure rates [96], [98], [162].”
Li, J., Wang, F., Liu, Q., Zhu, M., Huang, W., Huang, Z., Chen, E., Su, Y., & Wang, S. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539486 · Cited by 43 · see citing works
Self-citationQuestion Difficulty Prediction for Multiple Choice Problems in Medical Exams
Qiu, Z., Wu, X., & Fan, W. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358013 · Cited by 41 · see citing works
CASE STUDIES IN COMPUTER ADAPTIVE TEST DESIGN THROUGH SIMULATION1,2
Eignor, D. R., Stocking, M. L., Way, W. D., & Steffen, M. (1993) · ETS Research Report Series · doi:10.1002/j.2333-8504.1993.tb01567.x · Cited by 39 · cited 1× · see citing works
“This method has been widely adopted in high-stakes testing scenarios for humans, such as the SAT, GRE, and GMAT [5], [6].”
Assembling a Computerized Adaptive Testing Item Pool as a Set of Linear Tests
van der Linden, W. J., Ariel, A., & Veldkamp, B. P. (2006) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986031001081 · Cited by 39 · cited 1× · see citing works
“Amixed-integerprogramming[95]wasproposed tocreateabankthatsatisfiescontentspecificationsandmaxi-mizesinformationatselectedproficiencyvalues.”
Yin, Y., Liu, Q., Huang, Z., Chen, E., Tong, W., Wang, S., & Su, Y. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330900 · Cited by 39 · see citing works
Self-citationA Test-Theoretic Approach to Observed-Score Equating
van der Linden, W. J. (2000) · Psychometrika · doi:10.1007/bf02296337 · Cited by 38 · cited 1× · see citing works
“Many further studies about equating scores have been conducted [114], [115], [116].”
A New Derivation of the Rasch Model
Roskam, E. E., & Jansen, P. G. W. (1984) · Advances in psychology · doi:10.1016/s0166-4115(08)62094-4 · Cited by 37 · cited 1× · see citing works
“The primary goal of CAT is to accurately and efficiently estimate examinees’ true proficiency levels by having them answer questions.”
BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing
Ghosh, A., & Lan, A. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/332 · Cited by 33 · cited 4× · see citing works
“…parameter estimation problem with a focus on data efficiency [20], [21]: The objective is to determine the values of latent parameters within a model (i.e., the examinee’s true proficiency) using the minimum amount of observed data (i.e., the fewest possible questions answered by the examinee).”
InfluentialCompanion Proceedings of the ACM Web Conference 2024
(2024) · doi:10.1145/3589335 · Cited by 32 · see citing works
An Integer Programming Approach to Item Bank Design
van der Linden, W. J., Veldkamp, B. P., & Reese, L. M. (2000) · Applied Psychological Measurement · doi:10.1177/01466210022031570 · Cited by 31 · see citing works
Constructing Rotating Item Pools for Constrained Adaptive Testing
Ariel, A., Veldkamp, B. P., & van der Linden, W. J. (2004) · Journal of Educational Measurement · doi:10.1111/j.1745-3984.2004.tb01170.x · Cited by 31 · see citing works
Computerized Adaptive Testing for Public Opinion Surveys
Montgomery, J., & Cutler, J. (2013) · Political Analysis · doi:10.1093/pan/mps060 · Cited by 30 · cited 1× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
Item Response Ranking for Cognitive Diagnosis
Tong, S., Liu, Q., Yu, R., Huang, W., Huang, Z., Pardos, Z. A., & Jiang, W. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/241 · Cited by 30 · cited 1× · see citing works
“The selection algorithm is CAT’s core of implementing adaptivity and is the focal point of this survey.”
Self-citationUnderstanding and improving fairness in cognitive diagnosis
Zhang, Z., Wu, L., Liu, Q., Liu, J., Huang, Z., Yin, Y., Zhuang, Y., Gao, W., & Chen, E. (2024) · Science China Information Sciences · doi:10.1007/s11432-022-3852-0 · Cited by 28 · cited 1× · see citing works
“Many further studies about equating scores have been conducted [114], [115], [116].”
Self-citationGMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing
Wang, H., Long, T., Yin, L., Zhang, W., Xia, W., Hong, Q., Xia, D., Tang, R., & Yu, Y. H. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599367 · Cited by 27 · cited 3× · see citing works
“To achieve CAT’s goal in Definition 1, the reward function can be defined as the accuracy of proficiency estimation at each step 2 [70], [73], [75], i.e., (cid”
Fast Task Adaptation Based on the Combination of Model-Based and Gradient-Based Meta Learning
Xu, Z., Chen, X., & Cao, L. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3028378 · Cited by 25 · cited 1× · see citing works
“Then, the meta-learner leverages this knowledge to swiftly adapt to new, unseen tasks [149].”
Dual Adversarial Network for Deep Active Learning
Wang, S., Li, Y., Ma, K., Ma, R., Guan, H., & Zheng, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58586-0_40 · Cited by 25 · cited 1× · see citing works
“…lies in designing effective sample selection algorithms, typically based on two criteria: informativeness , selecting samples that reduce model uncertainty [131], and representativeness , selecting samples that reflect the overall data distribution[132], [133], or a combination of both [134].”
Self-citationShin, J., & Bulut, O. (2021) · Behavior Research Methods · doi:10.3758/s13428-021-01602-9 · Cited by 25 · cited 1× · see citing works
“These datasets are useful for validating the CAT system’s capability to estimate proficiencies accurately and to adapt to the simulated changes during the testing process.”
BAL: Balancing Diversity and Novelty for Active Learning
Li, J.-Y., Chen, P.-G., Yu, S., Liu, S., & Jia, J.-Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3345844 · Cited by 25 · cited 1× · see citing works
“…lies in designing effective sample selection algorithms, typically based on two criteria: informativeness , selecting samples that reduce model uncertainty [131], and representativeness , selecting samples that reflect the overall data distribution[132], [133], or a combination of both [134].”
Self-citationArtificial Intelligence in Computerized Adaptive Testing
Mujtaba, D. F., & Mahapatra, N. R. (2020) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci51800.2020.00116 · Cited by 24 · cited 1× · see citing works
“Moreover, practical CAT also involves ensuring reliability, fairness, search efficiency, etc.”
An On-Line POMDP Solver for Continuous Observation Spaces
Hoerger, M., & Kurniawati, H. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560943 · Cited by 23 · see citing works
Dual‐Objective Item Selection Criteria in Cognitive Diagnostic Computerized Adaptive Testing
Kang, H., Zhang, S., & Chang, H. (2017) · Journal of Educational Measurement · doi:10.1111/jedm.12139 · Cited by 22 · cited 1× · see citing works
“This has led to the development of dual-objective CD-CAT methods [66], [67], [128] that aim to assess both simultaneously.”
Item Response Theory for Efficient Human Evaluation of Chatbots
Sedoc, J., & Ungar, L. (2020) · Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP) · doi:10.18653/v1/2020.eval4nlp-1.3 · Cited by 22 · cited 1× · see citing works
“Recently, CAT has also been increasingly used to assess AI’s capabilities, such as textual entailment recognition, chat-bots, machine translation, and general-purpose AI systems [7], [8], [9], [10].”
BETA-CD: A Bayesian Meta-Learned Cognitive Diagnosis Framework for Personalized Learning
Bi, H., Chen, E., He, W., Wu, H., Zhao, W., Wang, S., & Wu, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25629 · Cited by 21 · see citing works
Self-citationItem Pool Design for an Operational Variable-Length Computerized Adaptive Test
He, W., & Reckase, M. D. (2013) · Educational and Psychological Measurement · doi:10.1177/0013164413509629 · Cited by 20 · cited 1× · see citing works
“They propose the bin-and-union method to allow a maximum deviation r between optimal difficulty and estimated proficiency, extending these methods for large-scale CAT systems and continuous new question pretesting [92], [93].”
Multiple Maximum Exposure Rates in Computerized Adaptive Testing
Barrada, J. R., Veldkamp, B. P., & Olea, J. (2008) · Applied Psychological Measurement · doi:10.1177/0146621608315329 · Cited by 19 · see citing works
Reinforcement Learning Applied to Adaptive Classification Testing
Nurakhmetov, D. (2019) · Methodology of educational measurement and assessment · doi:10.1007/978-3-030-18480-3_17 · Cited by 18 · cited 2× · see citing works
“Reinforcement learning (RL), a subfield of machine learning, is a powerful approach that enables an agent to learn how to make optimal decisions automatically [135].”
A Robust Computerized Adaptive Testing Approach in Educational Question Retrieval
Zhuang, Y., Liu, Q., Huang, Z., Li, Z., Jin, B., Bi, H., Chen, E., & Wang, S. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531928 · Cited by 18 · see citing works
Self-citationRethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling
Bao, S., Xu, Q., Yang, Z., Cao, X., & Huang, Q. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3141095 · Cited by 17 · see citing works
Zheng, Y., Cheon, H., & Katz, C. M. (2020) · Applied Psychological Measurement · doi:10.1177/0146621620931198 · Cited by 16 · cited 1× · see citing works
“In the Appendix, (onlineavailable)weshowtheunderlyingcausesandadvantages ofdifferentfactorsinCATtestcontrol.”
HmcNet: A General Approach for Hierarchical Multi-Label Classification
Huang, W., Chen, E., Liu, Q., Xiong, H., Huang, Z., Tong, S., & Zhang, D. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3207511 · Cited by 16 · see citing works
Self-citationExploration of Item Selection in Dual-Purpose Cognitive Diagnostic Computerized Adaptive Testing
Dai, B., Zhang, M., & Li, G. (2016) · Applied Psychological Measurement · doi:10.1177/0146621616666008 · Cited by 14 · cited 1× · see citing works
“This has led to the development of dual-objective CD-CAT methods [66], [67], [128] that aim to assess both simultaneously.”
IRT-based Aggregation Model of Crowdsourced Pairwise Comparison for Evaluating Machine Translations
Otani, N., Nakazawa, T., Kawahara, D., & Kurohashi, S. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1049 · Cited by 14 · cited 1× · see citing works
“Recently, CAT has also been increasingly used to assess AI’s capabilities, such as textual entailment recognition, chat-bots, machine translation, and general-purpose AI systems [7], [8], [9], [10].”
Robust Computerized Adaptive Testing
Veldkamp, B. P., & Verschoor, A. J. (2019) · Methodology of educational measurement and assessment · doi:10.1007/978-3-030-18480-3_15 · Cited by 14 · cited 1× · see citing works
“Veldkamp et al. [68] consider the uncertainty in question parameters during the selection process.”
A novel computerized adaptive testing framework with decoupled learning selector
Ma, H., Zeng, Y., Yang, S., Qin, C., Zhang, X., & Zhang, L. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01019-1 · Cited by 14 · see citing works
Self-citationBibliometric Analysis of Articles on Computerized Adaptive Testing
Yurtçu, M., & Güzeller, C. O. (2021) · Participatory Educational Research · doi:10.17275/per.21.98.8.4 · Cited by 13 · cited 1× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
Multifaceted Open Social Learner Modelling
Shi, L., Cristea, A. I., & Hadžidedić, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-09635-3_4 · Cited by 12 · see citing works
Search-Efficient Computerized Adaptive Testing
Hong, Y., Tong, S., Huang, W., Zhuang, Y., Liu, Q., Chen, E., Li, X., & He, Y. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615049 · Cited by 11 · see citing works
Self-citationXiong, J., Luo, Z., Luo, G., & Yu, X. (2022) · British Journal of Mathematical and Statistical Psychology · doi:10.1111/bmsp.12271 · Cited by 10 · cited 1× · see citing works
“2, we categorize existing CAT research into four major components involved in the testing process described above: 1) Measurement Model, 2) Selection Algorithm, 3) Question Bank Construction, and 4) Test Control.”
The Information Product Methods: A Unified Approach to Dual-Purpose Computerized Adaptive Testing
Zheng, C., He, G., & Chunlei, G. (2017) · Applied Psychological Measurement · doi:10.1177/0146621617730392 · Cited by 9 · cited 1× · see citing works
“…size T , such that the final step estimate ˆ θ T , derived from S and their corresponding response labels y , closely approximates the examinee’s true proficiency θ 0 : However, solving this optimization problem directly is impractical, as the true proficiency θ 0 is not observable, and even the…”
STAN: Adversarial Network for Cross-domain Question Difficulty Prediction
Huang, Y., Huang, W., Tong, S., Huang, Z., Liu, Q., Chen, E., Ma, J., Wan, L., & Wang, S. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00032 · Cited by 9 · see citing works
Self-citationApplying IRT to Estimate Learning Ability and K-means Clustering in Web based Learning
Chang, W.-C., & Yang, H.-C. (2009) · Journal of Software · doi:10.4304/jsw.4.2.167-174 · Cited by 8 · see citing works
Self-Attention Gated Cognitive Diagnosis For Faster Adaptive Educational Assessments
Pei, X., Yang, S., Huang, J., & Xu, C. (2022) · Proceedings · doi:10.1109/icdm54844.2022.00051 · Cited by 7 · see citing works
Multi-objective optimization of item selection in computerized adaptive testing
Mujtaba, D. F., & Mahapatra, N. R. (2021) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3449639.3459334 · Cited by 6 · cited 1× · see citing works
“For example, Mujtaba et al. [78] use the standard error of measurement as the objective F ( S ) , which provides a measure of confidence in an estimate from a test.”
Test Equating with the Rasch Model to Compare Pre-test and Post-test Measurements
Uzun, Z., & Öğretmen, T. (2021) · Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi · doi:10.21031/epod.957614 · Cited by 6 · see citing works
Fine-grained Main Ideas Extraction and Clustering of Online Course Reviews
Xiao, C., Shi, L., Cristea, A. I., Li, Z., & Pan, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-11644-5_24 · Cited by 6 · see citing works
Balancing Test Accuracy and Security in Computerized Adaptive Testing
Feng, W., Ghosh, A., Sireci, S. G., & Lan, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36272-9_60 · Cited by 6 · see citing works
Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training
Ning, Y., Huang, Z., Lin, X., Chen, E., Tong, S., Gong, Z., & Wang, S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26573 · Cited by 6 · see citing works
Self-citationSACAT: Student-Adaptive Computerized Adaptive Testing
Yu, J., Mu, Z., Lei, J., Yin, L., Xia, W., Yu, Y. H., & Long, T. (2023) · International Conference on Distributed Artificial Intelligence (DAI) · doi:10.1145/3627676.3627679 · Cited by 6 · cited 1× · see citing works
“Yu et al. [76] recently introduce the collaborative information of examinees in optimizing this bi-level problem, achieving fast convergence of proficiency estimation.”
Self-citationSIETTE: A Web-Based Tool for Adaptive Testing
Conejo, R., Guzmán, E., Millán, E., Trella, M., Pérez-de-la-Cruz, J.-L., & Ríos, A. (2004) · International Journal of Artificial Intelligence in Education · doi:10.3233/irg-2004-14(1)03 · Cited by 6 · cited 1× · see citing works
“Expert-based Characteristics Annotation: In expert-based annotation, domain experts assess question parameters, as seen in online CAT systems like SIETTE [152] and GenTAI [153].”
An Item Bank Calibration Method for a Computer Adaptive Test
Kozierkiewicz, A., & Poniatowski, R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-05476-6_38 · Cited by 5 · cited 1× · see citing works
“2, we categorize existing CAT research into four major components involved in the testing process described above: 1) Measurement Model, 2) Selection Algorithm, 3) Question Bank Construction, and 4) Test Control.”
Optimal Number of Strata for the Stratified Methods in Computerized Adaptive Testing
Barrada, J. R., Abad, F. J., & Olea, J. (2014) · The Spanish Journal of Psychology · doi:10.1017/sjp.2014.50 · Cited by 5 · see citing works
MATHCAT: A Flexible Testing System in Mathematics Education for Adults
Verschoor, A. J., & Straetmans, G. (2009) · Springer eBooks · doi:10.1007/978-0-387-85461-8_7 · Cited by 5 · see citing works
Evaluating General-Purpose AI with Psychometrics
Wang, X., Jiang, L., Stillwell, D. J., Chen, S., Sun, L., Luo, F., Xie, X., & Hernández-Orallo, J. (2026) · RiuNet (Universitat Politècnica de València) · doi:10.1145/3769688 · Cited by 5 · cited 1× · see citing works
“Recently, CAT has also been increasingly used to assess AI’s capabilities, such as textual entailment recognition, chat-bots, machine translation, and general-purpose AI systems [7], [8], [9], [10].”
Lei, S., Huang, W., Tong, S., Liu, Q., Huang, Z., Chen, E., & Su, Y. (2021) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/ickg52313.2021.00063 · Cited by 4 · cited 10× · see citing works
“By exploring the existing work in Measurement Model, Selection Algorithms, Question Bank Construction, and Test Control, the paper offers a unified framework and encompasses the entire life cycle of the CAT system.”
InfluentialSelf-citationComputerized Adaptive Testing: A Unified Approach Under Markov Decision Process
Gilavert, P., & Freire, V. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10522-7_40 · Cited by 4 · cited 2× · see citing works
“Reinforcement learning (RL), a subfield of machine learning, is a powerful approach that enables an agent to learn how to make optimal decisions automatically [135].”
Online Planning for Interactive-POMDPs using Nested Monte Carlo Tree Search
Schwartz, J., Zhou, R., & Kurniawati, H. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981713 · Cited by 4 · cited 1× · see citing works
“POMDPs can be solved by many algorithms, such as Grid-based algorithms [146], Monte Carlo tree search [147].”
Zheng, Y., Nydick, S. W., Huang, S.-J., & Zhang, S. (2024) · Educational Measurement: Issues and Practice · doi:10.1111/emip.12593 · Cited by 4 · cited 1× · see citing works
“…are designed to achieve two key objectives: (1) to use the responses to estimate an examinee’s proficiency θ such that it closely approximates the true proficiency θ 0 by the end of the test, and (2) to select the most valuable and fitting questions for each examinee, thereby reducing test length.”
Developing, Maintaining, and Renewing the Item Inventory to Support CBT
Mills, C. N., Potenza, M. T., Fremer, J. J., & Ward, W. C. (2005) · Routledge eBooks · doi:10.4324/9781410612250-14 · Cited by 3 · see citing works
Learning Evidential Cognitive Diagnosis Networks Robust to Response Bias
Liu, J., Hou, J., Zhang, N., Liu, Z., & He, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20500-2_14 · Cited by 3 · see citing works
Self-citationA Bounded Ability Estimation for Computerized Adaptive Testing
Zhuang, Y., Liu, Q., Zhao, G., Huang, Z., Huang, W., Pardos, Z. A., Chen, E., Wu, J., & Li, X. (2023) · neural information processing systems · doi:10.52202/075280-0111 · Cited by 3 · see citing works
Self-citationFairness in Computerized Testing: Detecting Item Bias using CATSIB with Impact Present
Chu, M.-W., & Lai, H. (2014) · Alberta Journal of Educational Research · doi:10.55016/ojs/ajer.v59i4.55750 · Cited by 2 · see citing works
EFFECT OF CONTENT BALANCING ON MEASUREMENT PRECISION IN COMPUTER ADAPTIVE TESTING APPLICATIONS
Öcal, İ. Ü., & Doğan, N. (2024) · Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi · doi:10.21031/epod.1438977 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Bachmann, F., van der Weijden, D., Heitz, L., Sarasua, C., & Bernstein, A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0322690 · Cited by 4 · see citing works
Dwahdh, L., & Al-Shraifin, N. K. (2025) · Eurasia Journal of Mathematics Science and Technology Education · doi:10.29333/ejmste/15897 · Cited by 3 · see citing works
Zheng, T., Jiang, Z., Liu, J., & Feng, S. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02671-w · Cited by 1 · see citing works
“Second, most widely used benchmarks consist of publicly available items, raising serious concerns about data contamination: if test questions have been included in a model ’ s training corpus, performance re fl ects memorization rather than genuine knowledge or reasoning 12,13 .”
Using Deep Reinforcement Learning to Decide Test Length
Zoucha, J., Himelfarb, I., & Tang, N.-E. (2025) · Educational and Psychological Measurement · doi:10.1177/00131644251332972
Adaptive Health Questionnaires: Methods, Implementation, and User Impact
Malanin, V. (2025) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2025.v07i03.45768
Customizable Bayesian adaptive testing with Python – The adaptivetesting package
Engicht, J., Bee, R. M., & Koch, T. (2026) · Behavior Research Methods · doi:10.3758/s13428-026-03079-w
Zhong, W., Zhang, G., & Tang, X. (2026) · doi:10.2196/preprints.99503
Optimizing Symptom Surveys with Machine Learning to Predict PTSD One Year Post-trauma
Prince, C., Xie, H., Grider, S. R., Wang, X., & Xu, K. S. (2026) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase69719.2026.00056
“The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. questions may be relevant to different patients, a problem often addressed by computerized adaptive testing/diagnosis (CAT/CAD) [4], [5].”
Variable‐Length Calibration Stopping Rules for Multidimensional Computerized Adaptive Testing
Pang, H., Qi, Y., He, Y., & Zhao, Y. (2026) · Journal of Educational Measurement · doi:10.1111/jedm.70063
Liu, W., & Wang, W. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426400598
- Authors
- Zhuang, Y., Liu, Q., Bi, H., Huang, Z., Huang, W., Li, J., Yu, J., Liu, Z., Hu, Z., Hong, Y., Pardos, Z. A., Ma, H., Zhu, M., Wang, S., & Chen, E.
- Affiliations
- University of Science and Technology of China (CN)
- State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
- University of California, Berkeley (US)
- Anhui University (CN)
- IFlyTek (China) (CN)
- ORCID
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2026-08
- Volume
- 48
- Issue
- 8
- Pages
- 8744-8763
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W7134966922
- Cited by
- 9
- References
- 150
- Citations by year
- 2026: 5 · 2025: 4
- FWCI
- 28.62
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2024YFC3308200)
- National Natural Science Foundation of China (62525606, 62441239, 62477044)
- Key Technologies R&D Program of Anhui Province (202423k09020039)
- Fundamental Research Funds for the Central Universities
- Young Elite Scientists Sponsorship Program by CAST (2024QNRC001)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Physical Sciences › Computer Science › Information Systems › Educational Technology and Assessment
- Keywords
- computerized adaptive testing, item bank construction, test control, measurement model, psychometrics, individualized assessment, test fairness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
