About this Model
PrediQT (Raz et al., 2026) is a neural network that is finetuned to score responses from the Alternative Questions task.
PrediQT currently only supports English responses, but the model should perform well on responses that have been translated to English via Google Translate.
How do I use PrediQT?
To have your responses scored, upload a CSV that has a column named 'response', which contains the participant's alternative questions. The algorithm is case sensitive for the 'response' column name, but it does not matter if other columns are present in the input CSV.
The algorithm will add two new columns to your CSV: one named 'prediction' which reflects the model's question complexity score, and another named 'modelname', which denotes the model providing the score.
Responses are scored on a 1 to 6 scale, where higher scores reflect more complex questions, correlated with the levels of Bloom's taxonomy. For more information on how the model was trained and its performance, check out the paper, or the model space on Hugging Face.
