A shallow neural network mapping item content features to 6-dimensional embeddings, fit jointly with latent abilities via Monte Carlo EM, achieves competitive held-out calibration on two Duolingo English Test task types.
AutoIRT: Calibrating Item Response Theory Models with Automated Machine Learning
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · Pith
abstract
Item response theory (IRT) is a class of interpretable factor models that are widely used in computerized adaptive tests (CATs), such as language proficiency tests. Traditionally, these are fit using parametric mixed effects models on the probability of a test taker getting the correct answer to a test item (i.e., question). Neural net extensions of these models, such as BertIRT, require specialized architectures and parameter tuning. We propose a multistage fitting procedure that is compatible with out-of-the-box Automated Machine Learning (AutoML) tools. It is based on a Monte Carlo EM (MCEM) outer loop with a two stage inner loop, which trains a non-parametric AutoML grade model using item features followed by an item specific parametric model. This greatly accelerates the modeling workflow for scoring tests. We demonstrate its effectiveness by applying it to the Duolingo English Test, a high stakes, online English proficiency test. We show that the resulting model is typically more well calibrated, gets better predictive performance, and more accurate scores than existing methods (non-explanatory IRT models and explanatory IRT models like BERT-IRT). Along the way, we provide a brief survey of machine learning methods for calibration of item parameters for CATs.
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Fine-tuned transformers with multi-task learning recover substantial wording-derived signal for item difficulty at small sample sizes typical in applied testing.
citing papers explorer
-
Learning Item Embeddings and Hyperparameters for IRT Calibration via Monte Carlo EM
A shallow neural network mapping item content features to 6-dimensional embeddings, fit jointly with latent abilities via Monte Carlo EM, achieves competitive held-out calibration on two Duolingo English Test task types.
-
Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
Fine-tuned transformers with multi-task learning recover substantial wording-derived signal for item difficulty at small sample sizes typical in applied testing.