@inproceedings{park-etal-2025-dataverse,
    title = "Dataverse: Open-Source {ETL} (Extract, Transform, Load) Pipeline for Large Language Models",
    author = "Park, Hyunbyung  and
      Lee, Sukyung  and
      Gim, Gyoungjin  and
      Kim, Yungi  and
      Kim, Dahyun  and
      Park, Chanjun",
    editor = "Dziri, Nouha  and
      Ren, Sean (Xiang)  and
      Diao, Shizhe",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-demo.1/",
    pages = "1--10",
    ISBN = "979-8-89176-191-9",
    abstract = "To address the challenges associated with data processing at scale, we propose Dataverse, a unified open-source Extract-Transform-Load (ETL) pipeline for large language models (LLMs) with a user-friendly design at its core. Easy addition of custom processors with block-based interface in Dataverse allows users to readily and efficiently use Dataverse to build their own ETL pipeline. We hope that Dataverse will serve as a vital tool for LLM development and open source the entire library to welcome community contribution. Additionally, we provide a concise, two-minute video demonstration of our system, illustrating its capabilities and implementation."
}