Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring

ArXi:2603.06066v1 Announce Type: cross Automated Essay Scoring (AES) has been explored for decades with the goal to teachers by reducing grading workload and mitigating subjective biases. While early systems relied on handcrafted features and statistical models, recent advances in Large Language Models (LLMs) have made it possible to evaluate student writing with unprecedented flexibility. This paper investigates the application of state-of-the-art open-weight LLMs for the grading of Austrian A-level German texts, with a particular focus on rubric-based evaluation.