Papers by Nikolay Alekseevich Butakov
SlideGuard: AI-Driven Evaluation of Graduate Student Presentation Materials (2026.acl-demo)
Copied to clipboard
Nikolay Alekseevich Butakov, Maria Khodorchenko, Mazein Nikita, Daniil Gareev, Yuri Falevskiy, Georgii Konev, Denis Nasonov
| Challenge: | Effective communication is a core objective of graduate education in AI and machine learning (ML). |
| Approach: | They propose an evaluation agent that assesses slide decks against a framework of expert-defined criteria using a visual language model. |
| Outcome: | The evaluation agent detects the majority of expert-identified issues on a dataset of 150 annotated slide decks and shows strong results on structural and visual criteria and known limitations on subjective dimensions such as research quality. |