2nd Workshop on Automated Evaluation of Learning and Assessment Content

📣 The proceedings are now online. 📣

Thanks to CEUR-WS.org for supporting our workshop!

Evaluation of learning and assessment content has always been a crucial task in the educational domain, but traditional approaches based on human feedback are not always usable in modern educational settings. Indeed, the advent of machine learning models, in particular Large Language Models (LLMs), enabled to quickly and automatically generate large quantities of data, making human evaluation unfeasible. Similarly, Massive Open Online Courses (MOOCs) have numbers of attending students so large that it is unsustainable to manually provide feedback to all of them. Thus, the need for accurate and automated techniques for evaluating educational content – e.g., questions, hints, and feedback – became pressing. Building on the success of the First Workshop on the Automatic Evaluation of Learning and Assessment Content, which was held at AIED 2024, this workshop aims to attract professionals from both academia and industry, and to offer an opportunity to discuss which are the common challenges in evaluating learning and assessment content and tools in education.