works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

physics.ed-ph2026

AI-based scoring systematically underestimates conceptual understanding of linguistically weak students' explanations in physics

Markus S. Feser, Paul L. Tschisgale

The study evaluates AI-based scoring of secondary students' physics explanations and finds that these systems systematically underestimate conceptual understanding for explanations…

physics.ed-ph2026

Developing an LLM-Based Feedback System Grounded in Evidence-Centered Design to Support Physics Problem Solving

Holger Maus, Fabian Kieser, Stefan Petersen +2

Generative AI offers new opportunities for individualized and adaptive learning, e.g., through large language model (LLM)-based feedback systems. While LLMs can produce factually c…

stat.AP2026

Daily and Weekly Periodicity in Large Language Model Performance and Its Implications for Research

Paul Tschisgale, Peter Wulff

Large language models (LLMs) are increasingly used in research as both tools and objects of study. Much of this work assumes that LLM performance under fixed conditions (identical…

cs.CL2025

Evaluating NLP Embedding Models for Handling Science-Specific Symbolic Expressions in Student Texts

Tom Bleckmann, Paul Tschisgale

In recent years, natural language processing (NLP) has become integral to educational data mining, particularly in the analysis of student-generated language products. For research…

physics.ed-ph2025

Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment

Paul Tschisgale, Holger Maus, Fabian Kieser +3

Large language models (LLMs) are now widely accessible, reaching learners at all educational levels. This development has raised concerns that their use may circumvent essential le…