@inproceedings{fan-etal-2025-bjtu,
    title = "{BJTU} at {BEA} 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating {AI} Math Tutors",
    author = "Fan, Yuming  and
      Tan, Chuangchuang  and
      Song, Wenyu",
    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-1.82/",
    pages = "1073--1077",
    ISBN = "979-8-89176-270-1",
    abstract = "We present a prompt-based evaluation framework for assessing AI-generated math tutoring responses across four pedagogical dimensions: mistake identification, mistake location, guidance quality, and actionability. Our approach leverages task-aware prompt tuning on a large language model, supplemented by data augmentation techniques including dialogue shuffling and class-balanced downsampling. In experiments on the BEA 2025 Shared Task benchmark, our system achieved first place in mistake identification and strong top-five rankings in the other tracks. These results demonstrate the effectiveness of structured prompting and targeted augmentation for enhancing LLMs' ability to provide pedagogically meaningful feedback."
}