ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios

Researchers Markus Bayer, Justin Lutz, and Christian Reuter published ActiveLLM in Transactions of the Association for Computational Linguistics (TACL) Volume 14, pages 1–22, a method that uses large language models including GPT-4, o1, Llama 3, and Mistral Large to select training instances for active learning. The authors report ActiveLLM significantly improves BERT classifier performance in few-shot scenarios, outperforming traditional active learning methods and improving the few-shot methods ADAPET, PERFECT, and SetFit, and that it can be extended to non-few-shot scenarios with iterative selections to help other active learning strategies overcome their cold-start problem.

Abstract 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. - Anthology ID: - 2026.tacl-1.1 - Volume: - Transactions of the Association for Computational Linguistics, Volume 14 https://aclanthology.org/volumes/2026.tacl-1/ - Month: - Year: - 2026 - Address: - Cambridge, MA - Venue: - TACL https://aclanthology.org/venues/tacl/ - SIG: - Publisher: - MIT Press - Note: - Pages: - 1–22 - Language: - URL: - https://aclanthology.org/2026.tacl-1.1/ https://aclanthology.org/2026.tacl-1.1/ - DOI: - 10.1162/tacl.a.63 https://doi.org/10.1162/tacl.a.63 - Cite ACL : - Markus Bayer, Justin Lutz, and Christian Reuter. 2026. ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios https://aclanthology.org/2026.tacl-1.1/ . Transactions of the Association for Computational Linguistics , 14:1–22. - Cite Informal : - ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios https://aclanthology.org/2026.tacl-1.1/ Bayer et al., TACL 2026 - PDF: - https://aclanthology.org/2026.tacl-1.1.pdf https://aclanthology.org/2026.tacl-1.1.pdf