# Entropy-aware Masking for Masked Language Modeling

arXiv: https://arxiv.org/abs/2605.28526 · HTML: https://mlsanity.com/paper/2605.28526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Should You Mask 15% in Masked Language Modeling?](https://mlsanity.com/paper/2202.08005/) (2022)
- [Train No Evil: Selective Masking for Task-Guided Pre-Training](https://mlsanity.com/paper/2004.09733/) (2020)

## Abstract (arXiv)

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context. This process enables the model to capture both syntactic and semantic properties of language. Conventionally, the tokens selected for masking are chosen at random, which may not always yield the most effective learning signals. In this work, we examine a token masking strategy based on entropy distribution. We use the model's entropy over token predictions to identify which tokens should be masked. This method aims to target tokens that are more informative and uncertain to improve the training efficacy. We also propose a novel self-masking approach that enhances training efficiency without relying on an external reference model. Experimental results demonstrate that our method achieves an average performance improvement of 5% in GLUE scores compared to the baseline. Further, we experiment with combining knowledge distillation with entropy masking, resulting in the best overall results.