ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios
Transactions of the Association for Computational Linguistics · 05.01.2026 · 14 · 1-22
DOI: 10.1162/tacl.a.63 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 05.01.2026. Verfasst von Markus Bayer und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Active learning is designed to minimize annotation efforts by prioritizing instances that most enhance learning. However, many active learning strategies struggle with a ‘cold-start’ problem, needing substantial initial data to be effective. This limitation reduces their utility in the increasingly relevant few-shot scenarios, where the instance selection has a substantial impact. To address this, we introduce ActiveLLM, a novel active learning approach that leverages Large Language Models such as GPT-4, o1, Llama 3, or Mistral Large for selecting instances. We demonstrate that ActiveLLM significantly enhances the classification performance of BERT classifiers in few-shot scenarios, outperforming traditional active learning methods as well as improving the few-shot learning methods ADAPET, PERFECT, and SetFit. Additionally, ActiveLLM can be extended to non-few-shot scenarios, allowing for iterative selections. In this way, ActiveLLM can even help other active learning strategies to overcome their cold-start problem. Our results suggest that ActiveLLM offers a promising solution for improving model performance across various learning setups.
Zitieren
APA
Bayer, M., Lutz, J., & Reuter, C. (2026). ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios. Transactions of the Association for Computational Linguistics, 14, 1-22. https://doi.org/10.1162/tacl.a.63
Vancouver
Bayer M, Lutz J, Reuter C. ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios. Transactions of the Association for Computational Linguistics. 2026;14:1-22. doi:10.1162/tacl.a.63
BibTeX
@article{Bayer2026,
author = {Bayer, Markus and Lutz, Justin and Reuter, Christian},
title = {ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios},
journal = {Transactions of the Association for Computational Linguistics},
year = {2026},
volume = {14},
pages = {1--22},
doi = {10.1162/tacl.a.63}
}
EUVIMED