@inproceedings{backer-hyman-2025-bootstrapping,
    title = "Bootstrapping {AI}: Interdisciplinary Approaches to Assessing {OCR} Quality in {E}nglish-Language Historical Documents",
    author = "Backer, Samuel  and
      Hyman, Louis",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.nlp4dh-1.21/",
    pages = "251--256",
    ISBN = "979-8-89176-234-3",
    abstract = "New LLM-based OCR and post-OCR correction methods promise to transform computational historical research, yet their efficacy remains contested. We compare multiple correction approaches, including methods for ``bootstrapping'' fine-tuning with LLM-generated data, and measure their effect on downstream tasks. Our results suggest that standard OCR metrics often underestimate performance gains for historical research, underscoring the need for discipline-driven evaluations that can better reflect the needs of computational humanists."
}