{"slug": "activellm-large-language-model-based-active-learning-for-textual-few-shot", "title": "ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios", "summary": "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.", "body_md": "##### Abstract\n\nActive 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.\n- Anthology ID:\n- 2026.tacl-1.1\n- Volume:\n- [Transactions of the Association for Computational Linguistics, Volume 14](https://aclanthology.org/volumes/2026.tacl-1/)\n- Month:\n- Year:\n- 2026\n- Address:\n- Cambridge, MA\n- Venue:\n- [TACL](https://aclanthology.org/venues/tacl/)\n- SIG:\n- Publisher:\n- MIT Press\n- Note:\n- Pages:\n- 1–22\n- Language:\n- URL:\n- [https://aclanthology.org/2026.tacl-1.1/](https://aclanthology.org/2026.tacl-1.1/)\n- DOI:\n- [10.1162/tacl.a.63](https://doi.org/10.1162/tacl.a.63)\n- Cite (ACL):\n- 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.\n- Cite (Informal):\n- [ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios](https://aclanthology.org/2026.tacl-1.1/) (Bayer et al., TACL 2026)\n- PDF:\n- [https://aclanthology.org/2026.tacl-1.1.pdf](https://aclanthology.org/2026.tacl-1.1.pdf)", "url": "https://wpnews.pro/news/activellm-large-language-model-based-active-learning-for-textual-few-shot", "canonical_source": "https://aclanthology.org/2026.tacl-1.1/", "published_at": "2026-10-07 00:00:00+00:00", "updated_at": "2026-10-08 00:17:48.503745+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "natural-language-processing", "ai-research"], "entities": ["ActiveLLM", "Markus Bayer", "Justin Lutz", "Christian Reuter", "Transactions of the Association for Computational Linguistics", "GPT-4", "Llama 3", "Mistral Large"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/activellm-large-language-model-based-active-learning-for-textual-few-shot", "markdown": "https://wpnews.pro/news/activellm-large-language-model-based-active-learning-for-textual-few-shot.md", "text": "https://wpnews.pro/news/activellm-large-language-model-based-active-learning-for-textual-few-shot.txt", "jsonld": "https://wpnews.pro/news/activellm-large-language-model-based-active-learning-for-textual-few-shot.jsonld"}}