@inproceedings{beigman-klebanov-etal-2026-data,
    title = "Data-lean fine-tuning of models for evaluating teacher performance in a {G}en{AI}-led elicitation simulation",
    author = "Beigman Klebanov, Beata  and
      Hoang, Andrew  and
      Mikeska, Jamie  and
      Longwill, Benny  and
      Kashyap, Sanjna  and
      Halder, Shreyashi  and
      Bhatia, Aakanksha",
    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-1.38/",
    pages = "546--561",
    ISBN = "979-8-89176-409-5",
    abstract = "Recent advances in the capabilities of conversational agents based on large language models make them a very promising tool for role playing K-12 students in order to train educators in conversational teaching practices, such as eliciting student thinking, explaining disciplinary content, and facilitating a classroom discussion. In fact, such simulations can and have been developed relatively quickly and without data to machine-learn from {--} neither classroom data nor human-simulated data. To enhance the usefulness and effectiveness of such teaching simulations, it is necessary to provide pedagogically sound, timely, and personalized feedback to the educator about their simulation performance. In this study, we present experiments on fine-tuning models to evaluate educator performance in an elicitation teaching simulation. The models are developed with data collected during usability testing of the simulation and evaluated on real user data. We show that even with relatively little fine-tuning data, robust performance can be obtained"
}