@article{foppiano-etal-2026-scilad,
    title = "{S}ci{L}a{D}: A Large-Scale, Transparent, Reproducible Dataset for Natural Scientific Language Processing",
    author = "Foppiano, Luca  and
      Takeshita, Sotaro  and
      Ortiz Suarez, Pedro  and
      Borisova, Ekaterina  and
      Abu Ahmad, Raia  and
      Ostendorff, Malte  and
      Barth, Fabio  and
      Moreno-Schneider, Julian  and
      Rehm, Georg",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.603/",
    pages = "7606--7618",
    abstract = "SciLaD is a novel, large-scale dataset of scientific language constructed entirely using open-source frameworks and publicly available data sources. It comprises a curated English split containing over 10 million scientific publications and a multilingual, unfiltered TEI XML split including more than 35 million publications. We also publish the extensible pipeline for generating SciLaD. The dataset construction and processing workflow demonstrates how open-source tools can enable large-scale, scientific data curation while maintaining high data quality. Finally, we pre-train a RoBERTa model on our dataset and evaluate it across a comprehensive set of benchmarks, achieving performance comparable to other scientific language models of similar size, validating the quality and utility of SciLaD. We publish the dataset and evaluation pipeline to promote reproducibility, transparency, and further research in natural scientific language processing and understanding including scholarly document processing."
}