The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models
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 Maskability Index (MI), a quantitative metric that estimates whether a knowledge relation is better suited to masked-style prompting or prefix-style prompting in few-shot generation. MI is computed from differences in DepthRank scores between masked and unmasked templates, providing a principled measure of objective-template a
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Understanding large language models demands distinguishing human projection from machine cognition - Nature →
- FuzzySimilar title/name (fuzzy) · 59%run-llama/llama_index →
“Fuzzy title match (0.73): “The Maskability Index: Predicting Task-Objective Alignment i” ≈ “run-llama/llama_index””
- FuzzySimilar title/name (fuzzy) · 59%VectifyAI/PageIndex →
“Fuzzy title match (0.73): “The Maskability Index: Predicting Task-Objective Alignment i” ≈ “VectifyAI/PageIndex””
- LinkedLinked via arxiv author · 85%Ahmad Pouramini →
“The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models”
- LinkedLinked via arxiv author · 85%Mahsa Afsharzadeh →
“The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models”