Mahsa Afsharzadeh

The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models

Ahmad Pouramini, Mahsa Afsharzadeh

Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating structured knowledge. However, their performance depends on how closely the prompting strategy matches the objectives used during pretraining. We introduce the Maskabil…Read more