Author: Sebastian Gombert

In a recent study, we explored how students’ conceptual understanding develops throughout a digitally supported chemistry unit on chemical kinetics. Working with approximately 300 upper-secondary students, we combined automated scoring of students’ written responses and other learning artifacts with network analysis techniques to model the growth of individual knowledge structures over time. The results showed that transformer-based language models can reliably identify and score chemistry-related knowledge elements from classroom data, enabling the construction of longitudinal knowledge networks that reflect how students connect scientific concepts. Several network characteristics were associated with students’ posttest performance, suggesting that these representations capture meaningful aspects of learning progress. The findings highlight the potential of combining automated assessment and learning analytics to provide teachers with real-time insights into students’ developing understanding and to support adaptive instructional…

At this year's JTEL Summer school, Sebastian Gombert and Amir Rajabi from DIPF hosted a workshop on Natural Language Processing (NLP) for Education and Research. Participants explored how modern language technologies can support both educational practice and scientific inquiry. The session introduced core NLP concepts and discussed applications ranging from automated assessment and feedback generation to classroom discourse analysis, literature synthesis, and retrieval-augmented generation. Following the introductory presentation, participants worked collaboratively in small groups to design NLP-based solutions for real-world challenges. Drawing on both provided examples and their own research interests, attendees developed concepts for systems such as educational recommender tools, feedback assistants, and research support applications. Interactive collaboration was supported through discussion, sketching, and digital whiteboarding. The workshop highlighted not only the growing potential of large language models and…

On 01. Mai, Longwei Cong presented his paper “Automatic Short Answer Grading with LLMs: From Memorization to Reasoning” at the 16th International Conference on Learning Analytics and Knowledge. The paper examines the performance of fine-tuned PLMs and LLMs across different dataset sizes and compares them with prompt-based approaches for automatic short answer grading. The results show that fine-tuned LLMs and rubric-based prompting can match or even exceed the performance of BERT-based models. In particular, rubric-based prompting with open-weight models can deliver competitive results without requiring annotated training data or hardware-intensive fine-tuning, while also helping to address data protection concerns. This work provides empirical evidence for the role of LLMs in automatic short answer grading and opens up future research directions on resource-efficient, interpretable, and reasoning-driven grading. You can find the…

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…

Language learners make the fastest progress when reading texts that match their proficiency level. But most real-world texts are too hard—and manually adapting them is time-consuming. So the big question is: Can AI automatically simplify texts to a specific CEFR level without losing meaning? We explored exactly this in the TSAR 2025 Shared Task, where systems had to rewrite advanced English texts (B2+) to easier levels like A2 or B1. Our team submitted two different approaches: EZ-SCALAR and SAGA. EZ-SCALAR works like an expert panel of AI models. Two large language models (GPT-5 and Claude) each produce their own simplification, critique each other, refine their versions, and then a final “judge” model picks the best result. An extended version, EZ-SCALAR Lex, adds something extra: a vocabulary check using EFLLex, a…

Helping students apply energy ideas to everyday situations is a core goal in physics education. But not all students get there—and it’s not just about who knows the most content. In a 10-week classroom study with 165 students, we tracked both their energy understanding and their affective and metacognitive factors (like emotions, cognitive load, and self-regulation). Using k-means clustering on their learning trajectories, we identified three distinct student groups that differed in the coherence of their energy knowledge development. The key insight: Students who learned the most also felt more positive, experienced lower cognitive load, and used stronger metacognitive strategies. Those who struggled often felt overwhelmed or disengaged. The takeaway is clear: supporting emotions and self-regulation is just as important as teaching physics content. Instruction that addresses these factors can…