@inproceedings{mulcaire-madnani-2025-span,
    title = "Span Labeling with Large Language Models: Shell vs. Meat",
    author = "Mulcaire, Phoebe  and
      Madnani, Nitin",
    editor = {Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Ana{\"i}s  and
      Yaneva, Victoria  and
      Yuan, Zheng},
    booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bea-1.62/",
    pages = "850--859",
    ISBN = "979-8-89176-270-1",
    abstract = "We present a method for labeling spans of text with large language models (LLMs) and apply it to the task of identifying shell language, language which plays a structural or connective role without constituting the main content of a text. We compare several recent LLMs by evaluating their ``annotations'' against a small human-curated test set, and train a smaller supervised model on thousands of LLM-annotated examples. The described method enables workflows that can learn complex or nuanced linguistic phenomena without tedious, large-scale hand-annotations of training data or specialized feature engineering."
}