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

arXiv: https://arxiv.org/abs/2607.20265 · HTML: https://mlsanity.com/paper/2607.20265/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements](https://mlsanity.com/paper/2305.03695/) (2023)
- [Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning](https://mlsanity.com/paper/2210.12217/) (2022)
- [Retrieval Augmentation for Commonsense Reasoning: A Unified Approach](https://mlsanity.com/paper/2210.12887/) (2022)
- [ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems](https://mlsanity.com/paper/2305.07797/) (2023)
- [Constrained Text Generation with Global Guidance -- Case Study on CommonGen](https://mlsanity.com/paper/2103.07170/) (2021)
- [ALBERT with Knowledge Graph Encoder Utilizing Semantic Similarity for Commonsense Question Answering](https://mlsanity.com/paper/2211.07065/) (2022)
- [Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge](https://mlsanity.com/paper/2105.13607/) (2021)
- [BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation](https://mlsanity.com/paper/2310.17054/) (2023)
- [Estimating Commonsense Plausibility through Semantic Shifts](https://mlsanity.com/paper/2502.13464/) (2025)
- [Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models](https://mlsanity.com/paper/2606.24841/) (2026)

## Abstract (arXiv)

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 alignment. We evaluate MI on a diverse set of relations from the ATOMIC2020 knowledge base completion benchmark and show that it is positively correlated with downstream generation performance. These results indicate that MI can help select appropriate prompting templates and adaptation strategies for extracting relational knowledge from pretrained language models, especially in low-resource settings.