@inproceedings{bhattacharyya-etal-2025-lexilogic-bea,
    title = "{L}exi{L}ogic at {BEA} 2025 Shared Task: Fine-tuning Transformer Language Models for the Pedagogical Skill Evaluation of {LLM}-based tutors",
    author = "Bhattacharyya, Souvik  and
      Roy, Billodal  and
      M, Niranjan  and
      Gupta, Pranav",
    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-1.93/",
    pages = "1180--1186",
    ISBN = "979-8-89176-270-1",
    abstract = "While large language models show promise as AI tutors, evaluating their pedagogical capabilities remains challenging. In this paper, we, team LexiLogic presents our participation in the BEA 2025 shared task on evaluating AI tutors across five dimensions: Mistake Identification, Mistake Location, Providing Guidance, Actionability, and Tutor Identification. We approach all tracks as classification tasks using fine-tuned transformer models on a dataset of 300 educational dialogues between a student and a tutor in the mathematical domain. Our results show varying performance across tracks, with macro average F1 scores ranging from 0.47 to 0.82, achieving rankings between 4th and 31st place. Such models have the potential to be used in developing automated scoring metrics for assessing the pedagogical skills of AI math tutors."
}