mlsanityData to 7 Oct 2026

Variational Item Response Theory: Fast, Accurate, and Expressive

arXiv 2002.00276 ↗First posted 1 Feb 2020cs.LG stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

Item Response Theory (IRT) is a ubiquitous model for understanding humans based on their responses to questions, used in fields as diverse as education, medicine and psychology. Large modern datasets offer opportunities to capture more nuances in human behavior, potentially improving test scoring and better informing public policy. Yet larger datasets pose a difficult speed / accuracy challenge to contemporary algorithms for fitting IRT models. We introduce a variational Bayesian inference algorithm for IRT, and show that it is fast and scaleable without sacrificing accuracy. Using this inference approach we then extend classic IRT with expressive Bayesian models of responses. Applying this method to five large-scale item response datasets from cognitive science and education yields higher log likelihoods and improvements in imputing missing data. The algorithm implementation is open-source, and easily usable.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 7; 2024: 8; 2025: 5; 2026: 5.

29 papers.

Sort:

By area:

  1. 2023Position: AI Evaluation Should Learn from How We Test Humanscited by 36
  2. 2025Reliable and Efficient Amortized Model-based Evaluationcited by 29
  3. 2025How to Select Datapoints for Efficient Human Evaluation of NLG Models?cited by 23
  4. 2022py-irt: A Scalable Item Response Theory Library for Pythoncited by 19
  5. 2024Psychometric Alignment: Capturing Human Knowledge Distributions via Language Modelscited by 18
  6. 2024Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testingcited by 17
  7. 2024Generative AI for Education (GAIED): Advances, Opportunities, and Challengescited by 13
  8. 2023Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigmcited by 9
  9. 2024A Survey of Models for Cognitive Diagnosis: New Developments and Future Directionscited by 7
  10. 2022Foundation Posteriors for Approximate Probabilistic Inferencecited by 6
  11. 2023Knowledge Graph Enhanced Intelligent Tutoring System Based on Exercise Representativeness and Informativenesscited by 6
  12. 2024Survey of Computerized Adaptive Testing: A Machine Learning Perspectivecited by 6
17 more
  1. 2024A Psychology-based Unified Dynamic Framework for Curriculum Learningcited by 6
  2. 2024Provably Scalable Black-Box Variational Inference with Structured Variational Familiescited by 4
  3. 2023Transferable Curricula through Difficulty Conditioned Generatorscited by 3
  4. 2026Can We Trust Item Response Theory for AI Evaluation?cited by 3
  5. 2023Computational modeling of semantic changecited by 2
  6. 2023Training Reinforcement Learning Agents and Humans With Difficulty-Conditioned Generatorscited by 2
  7. 2025Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithmcited by 1
  8. 2025Just Read the Question: Enabling Generalization to New Assessment Items with Text Awarenesscited by 1
  9. 2021Deep Learning-Based Estimation and Goodness-of-Fit for Large-Scale Confirmatory Item Factor Analysiscited by 0
  10. 2022Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systemscited by 0
  11. 2023Amortised Design Optimization for Item Response Theorycited by 0
  12. 2024Introducing Flexible Monotone Multiple Choice Item Response Theory Models and Bit Scalescited by 0
  13. 2025Generative Cognitive Diagnosiscited by 0
  14. 2026An Interpretable and Scalable Framework for Evaluating Large Language Modelscited by 0
  15. 2026Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimationcited by 0
  16. 2026UNVaMP: Neural Knowledge Tracing with Variational Regularization of Latent Knowledge Dynamicscited by 0
  17. 2026Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluationcited by 0