activity
20242026
collaborators
Showing physics.ed-phShow all

5 papers · 1 filter

physics.ed-ph2026

Testing the Validity of Embedding-Based Similarity and Clustering for Handwritten Physics Solutions

Maike Tauschhuber, Gerd Kortemeyer

Text embeddings are increasingly used in physics education research to organize, compare, and cluster large collections of written text. Their appeal is clear: once student respons…

physics.ed-ph2026

When AI Evaluates Its Own Work: Validating Learner-Initiated, AI-Generated Physics Practice Problems

Tobias Geisler, Gerd Kortemeyer

Large language models (LLMs) can now generate physics practice problems in real time, yet the educational value of these items hinges on rapid, reliable post-generation vetting. In…

physics.ed-ph2025

The Boiling-Frog Problem of Physics Education

Gerd Kortemeyer

It is astonishing how rapidly general-purpose AI has crossed familiar thresholds in introductory physics. Comparing outputs from successive models, GPT-5 Thinking moves far beyond…

physics.ed-ph2024

Assessing Confidence in AI-Assisted Grading of Physics Exams through Psychometrics: An Exploratory Study

Gerd Kortemeyer, Julian Nöhl

This study explores the use of artificial intelligence in grading high-stakes physics exams, emphasizing the application of psychometric methods, particularly Item Response Theory…

physics.ed-ph2024

Grading Assistance for a Handwritten Thermodynamics Exam using Artificial Intelligence: An Exploratory Study

Gerd Kortemeyer, Julian Nöhl, Daria Onishchuk

Using a high-stakes thermodynamics exam as sample (252~students, four multipart problems), we investigate the viability of four workflows for AI-assisted grading of handwritten stu…