@article{tremblay-taillon-langlais-2026-escibench,
    title = "e{S}ci{B}ench: An Extensible Scientific {PDF} Extraction Benchmark",
    author = "Tremblay Taillon, Noah  and
      Langlais, Phillippe",
    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.600/",
    pages = "7568--7580",
    abstract = "Automatically extracting information from PDF documents (such as authors, affiliations, references, tables, equations) may be transformative in Digital Humanities where meta-data accompanying a document is typically manually collected, a cumbersome process. In this work, we conduct a systematic benchmarking of PDF extractors on a set of 100 scientific articles (1949 pages) of the STEM domain that have been processed automatically, then carefully curated. Our benchmark, named eSciBench is openly accessible. Putting to the test 13 extractors on it reveals that although some extractors perform well overall, extracting information from scientific articles is far from a solved problem."
}