@inproceedings{du-etal-2025-dvagen,
    title = "{DVAG}en: Dynamic Vocabulary Augmented Generation",
    author = "Du, Wei  and
      Liu, Nuowei  and
      Wang, Jie  and
      Kuang, Jiahao  and
      Ji, Tao  and
      Wang, Xiaoling  and
      Wu, Yuanbin",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.26/",
    pages = "365--372",
    ISBN = "979-8-89176-334-0",
    abstract = "Language models trained with a fixed vocabulary struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations. Existing dynamic vocabulary approaches attempt to address this limitation but face challenges such as fragmented codebases, lack of support for modern LLMs, and limited inference scalability. To overcome these issues, we introduce DVAGen, a fully open-source, unified framework designed for training, evaluation, and visualization of dynamic vocabulary-augmented language models. Our framework modularizes the pipeline for ease of customization, integrates seamlessly with open-source LLMs, and is the first to provide both CLI and WebUI tools for real-time result inspection. We validate the effectiveness of dynamic vocabulary methods on modern LLMs and demonstrate support for batch inference, significantly improving inference throughput."
}