@inproceedings{lade-etal-2026-domain,
    title = "Domain-Adaptive Pre-training for Automated Short Answer Grading in Conceptual Physics: Reliability, Question-Level Analysis, and Error Reduction",
    author = "Lade, Shirin  and
      Willis, Alistair  and
      Nylk, Jonathan  and
      Howson, Oli",
    editor = "Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bann{\`o}, Stefano  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Anais  and
      Yaneva, Victoria  and
      Yuan, Zheng",
    booktitle = "Proceedings of the 21st Workshop on Innovative Use of {NLP} for Building Educational Applications ({BEA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bea-1.45/",
    pages = "635--650",
    ISBN = "979-8-89176-409-5",
    abstract = "This paper investigates whether automated short answer grading can reliably support teachers when marking conceptual physics responses in settings with limited labelled data. Using free-text responses derived from Force Concept Inventory-style questions, the study shows that incorporating subject-specific knowledge improves grading consistency, particularly in early deployment scenarios. The system reduces grading errors and provides more reliable agreement with reference judgments, especially for more challenging questions. These results suggest that automated grading can assist teachers by supporting marking decisions and prioritising responses for review, while still requiring human oversight."
}