Papers › On the Importance of Effectively Adapting Pretrained Language Models for Active Learning

On the Importance of Effectively Adapting Pretrained Language Models for Active Learning

16 Apr 2021ACL 2022 5arXiv:2104.08320archive 2025-07-28

Katerina Margatina, Loïc Barrault, Nikolaos Aletras

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL and we explore ways to address this issue. We suggest to first adapt the pretrained LM to the target task by continuing training with all the available unlabeled data and then use it for AL. We also propose a simple yet effective fine-tuning method to ensure that the adapted LM is properly trained in both low and high resource scenarios during AL. Our experiments demonstrate that our approach provides substantial data efficiency improvements compared to the standard fine-tuning approach, suggesting that a poor training strategy can be catastrophic for AL.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mourga/contrastive-active-learning officialmentioned in paperpytorchGPL-3.0 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

Active LearningNatural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutMonte Carlo Dropout

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