@inproceedings{asano-etal-2025-exploring,
    title = "Exploring task formulation strategies to evaluate the coherence of classroom discussions with {GPT}-4o",
    author = "Asano, Yuya  and
      Beigman Klebanov, Beata  and
      Mikeska, Jamie",
    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/transition-to-people-yaml/2025.bea-1.52/",
    doi = "10.18653/v1/2025.bea-1.52",
    pages = "716--736",
    ISBN = "979-8-89176-270-1",
    abstract = "Engaging students in a coherent classroom discussion is one aspect of high-quality instruction and is an important skill that requires practice to acquire. With the goal of providing teachers with formative feedback on their classroom discussions, we investigate automated means for evaluating teachers' ability to lead coherent discussions in simulated classrooms. While prior work has shown the effectiveness of large language models (LLMs) in assessing the coherence of relatively short texts, it has also found that LLMs struggle when assessing instructional quality. We evaluate the generalizability of task formulation strategies for assessing the coherence of classroom discussions across different subject domains using GPT-4o and discuss how these formulations address the previously reported challenges{---}the overestimation of instructional quality and the inability to extract relevant parts of discussions. Finally, we report lack of generalizability across domains and the misalignment with humans in the use of evidence from discussions as remaining challenges."
}