Papers › Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text

18 Feb 2025arXiv:2502.12953archive 2025-07-28

Andrei Jarca, Florinel Alin Croitoru, Radu Tudor Ionescu

Masked language modeling has become a widely adopted unsupervised technique to pre-train language models. However, the process of selecting tokens for masking is random, and the percentage of masked tokens is typically fixed for the entire training process. In this paper, we propose to adjust the masking ratio and to decide which tokens to mask based on a novel task-informed anti-curriculum learning scheme. First, we harness task-specific knowledge about useful and harmful tokens in order to determine which tokens to mask. Second, we propose a cyclic decaying masking ratio, which corresponds to an anti-curriculum schedule (from hard to easy). We exemplify our novel task-informed anti-curriculum by masking (TIACBM) approach across three diverse downstream tasks: sentiment analysis, text classification by topic, and authorship attribution. Our findings suggest that TIACBM enhances the ability of the model to focus on key task-relevant features, contributing to statistically significant performance gains across tasks. We release our code at https://github.com/JarcaAndrei/TIACBM.

PaperPDFCode

Code

jarcaandrei/tiacbm officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Authorship AttributionLanguage ModelingLanguage ModellingMasked Language ModelingMulti-Label Text ClassificationSentiment AnalysisText Classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Text Classification Reuters-21578 TIACBM Micro-F1 91.2±0.20 #1 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections