@inproceedings{elaraby-litman-2025-lessons,
    title = "Lessons Learned in Assessing Student Reflections with {LLM}s",
    author = "Elaraby, Mohamed  and
      Litman, Diane",
    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-1.48/",
    pages = "672--686",
    ISBN = "979-8-89176-270-1",
    abstract = "Advances in Large Language Models (LLMs) have sparked growing interest in their potential as explainable text evaluators. While LLMs have shown promise in assessing machine-generated texts in tasks such as summarization and machine translation, their effectiveness in evaluating human-written content{---}such as student writing in classroom settings{---}remains underexplored. In this paper, we investigate LLM-based specificity assessment of student reflections written in response to prompts, using three instruction-tuned models. Our findings indicate that although LLMs may underperform compared to simpler supervised baselines in terms of scoring accuracy, they offer a valuable interpretability advantage. Specifically, LLMs can generate user-friendly explanations that enhance the transparency and usability of automated specificity scoring systems."
}