Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28526 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916055966810112 |
|---|---|
| author | Srinivasagan, Gokul Hartung, Kai Georges, Munir |
| author_facet | Srinivasagan, Gokul Hartung, Kai Georges, Munir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28526 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Entropy-aware Masking for Masked Language Modeling Srinivasagan, Gokul Hartung, Kai Georges, Munir Artificial Intelligence Computation and Language 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. |
| title | Entropy-aware Masking for Masked Language Modeling |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.28526 |