@inproceedings{tsvigun-etal-2025-atgen,
    title = "{ATG}en: A Framework for Active Text Generation",
    author = "Tsvigun, Akim  and
      Vasilev, Daniil  and
      Tsvigun, Ivan  and
      Lysenko, Ivan  and
      Bektleuov, Talgat  and
      Medvedev, Aleksandr  and
      Vinogradova, Uliana  and
      Severin, Nikita  and
      Mozikov, Mikhail  and
      Savchenko, Andrey  and
      Makarov, Ilya  and
      Rostislav, Grigorev  and
      Kuleev, Ramil  and
      Zhdanov, Fedor  and
      Shelmanov, Artem",
    editor = "Mishra, Pushkar  and
      Muresan, Smaranda  and
      Yu, Tao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-demo.63/",
    pages = "653--665",
    ISBN = "979-8-89176-253-4",
    abstract = "Active learning (AL) has demonstrated remarkable potential in reducing the annotation effort required for training machine learning models. However, despite the surging popularity of natural language generation (NLG) tasks in recent years, the application of AL to NLG has been limited. In this paper, we introduce Active Text Generation (ATGen) - a comprehensive framework that bridges AL with text generation tasks, enabling the application of state-of-the-art AL strategies to NLG. Our framework simplifies AL-empowered annotation in NLG tasks using both human annotators and automatic annotation agents based on large language models (LLMs). The framework supports LLMs deployed as a service, such as ChatGPT and Claude, or operated on-premises. Furthermore, ATGen provides a unified platform for smooth implementation and benchmarking of novel AL strategies tailored to NLG tasks. Finally, we present experimental results across multiple text generation tasks where we compare the performance of state-of-the-art AL strategies in various settings. We demonstrate that ATGen can reduce both the effort of human annotators and costs for API calls to automatic annotation agents based on LLMs."
}