@inproceedings{butakov-etal-2026-slideguard,
    title = "{S}lide{G}uard: {AI}-Driven Evaluation of Graduate Student Presentation Materials",
    author = "Butakov, Nikolay Alekseevich  and
      Khodorchenko, Maria  and
      Nikita, Mazein  and
      Gareev, Daniil  and
      Falevskiy, Yuri  and
      Konev, Georgii  and
      Nasonov, Denis",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.77/",
    pages = "785--793",
    ISBN = "979-8-89176-392-0",
    abstract = "Preparing graduate students for effective professional communication remains a central goal of higher education, yet consistently assessing the quality of presentation slide decks - particularly in fast-growing AI/ML programs - poses significant challenges.We introduce SlideGuard, an evaluation agent that assesses slide decks against a comprehensive framework of expert-defined criteria using a visual language model.The criteria, developed in collaboration with domain experts, span visual design, narrative coherence, and argumentative structure.SlideGuard delivers explicit, interpretable justifications for its scoring decisions, and its content-hash-based caching enables efficient re-evaluation after incremental edits, reducing the time educators spend on slide deck evaluation and accelerating feedback delivery to students.We evaluate the approach on a dataset of 150 annotated slide decks and show that it detects the majority of expert-identified issues, with stronger results on structural and visual criteria and known limitations on subjective dimensions such as research quality.SlideGuard is released under the Apache{~}2.0 license and is available on GitHub,[{\ensuremath{<}}https://github.com/Industrial-AI-Research-Lab/SlideGuard{\ensuremath{>}}] including all criterion prompts, configuration files, and evaluation scripts to facilitate replication."
}