Year: 2026

Rubrics are everywhere in education — but surprisingly, most AI systems for grading short answers barely use them. In our recent paper, Are Rubrics All You Need?, presented by Sebastian Gombert at the LAK 2026, we introduce rubric-based automatic short-answer scoring, a new approach where AI models explicitly align student answers with rubric criteria instead of treating grading as a black-box classification problem. We propose two novel architectures, GRAASP and ToLeGRAA, which use transformer-based alignment mechanisms to compare learner responses directly against rubric descriptions. Across German and English benchmark datasets, the models achieved highly competitive performance and transferred better to unseen questions than traditional instance-based classifiers. Particularly exciting is ToLeGRAA’s ability to generate token-level alignment maps, making it possible to visualize which parts of a student answer correspond to specific…

Are you a researcher in AI in education and/or natural language processing? Do you like shared tasks and machine learning competitions like the yearly SemEval tasks or Kaggle competitions? Then you might consider participating in the BEA 2026 Shared Task on Rubric-based Short Answer Scoring for German, co-organized by us and colleagues from IPN - Leibniz-Institut für die Pädagogik der Naturwissenschaften und Mathematik. For this shared task, we look at the natural language understanding task of rubric-based short answer scoring, a task for which models must score short answers to open-ended assessment questions with the help of provided textual scoring rubrics. The dataset we provide for this was collected in authentic German school contexts and scored by domain experts as part of the ALICE project funded by the Leibniz-Gemeinschaft. As…