@inproceedings{piktus-etal-2023-roots,
    title = "The {ROOTS} Search Tool: Data Transparency for {LLM}s",
    author = "Piktus, Aleksandra  and
      Akiki, Christopher  and
      Villegas, Paulo  and
      Lauren{\c{c}}on, Hugo  and
      Dupont, G{\'e}rard  and
      Luccioni, Sasha  and
      Jernite, Yacine  and
      Rogers, Anna",
    editor = "Bollegala, Danushka  and
      Huang, Ruihong  and
      Ritter, Alan",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-demo.29",
    doi = "10.18653/v1/2023.acl-demo.29",
    pages = "304--314",
    abstract = "ROOTS is a 1.6TB multilingual text corpus developed for the training of BLOOM, currently the largest language model explicitly accompanied by commensurate data governance efforts. In continuation of these efforts, we present the ROOTS Search Tool: a search engine over the entire ROOTS corpus offering both fuzzy and exact search capabilities. ROOTS is the largest corpus to date that can be investigated this way. The ROOTS Search Tool is open-sourced and available on Hugging Face Spaces: \url{https://huggingface.co/spaces/bigscience-data/roots-search}. We describe our implementation and the possible use cases of our tool.",
}