RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting in Rubric-based Scoring for German

TL;DR

This paper introduces Meta-prompting, a novel method where LLMs generate custom prompts for rubric-based scoring of German student answers, showing competitive results in shared task tracks.

Contribution

The paper presents Meta-prompting as a new approach for rubric-based scoring, combining prompt generation with traditional and fine-tuning methods for improved performance.

Findings

Meta-prompting achieved 6th place in Track 1 with QWK 0.729

Secured 4th place in Track 3 with QWK 0.674

Placed 4th in Track 4 with QWK 0.49

Abstract

In this paper, we present the RETUYT-INCO participation at the BEA 2026 shared task "Rubric-based Short Answer Scoring for German". Our team participated in track 1 (Unseen answers three-way), track 3 (Unseen answers two-way) and track 4 (Unseen questions two-way). Since these tracks required scoring short student answers using specific rubrics, we looked for ways to handle the changing nature of the task. We created a method called Meta-prompting. In this approach, an LLM creates a custom prompt based on examples from the Train set. This prompt is then used to grade new student answers. Along with this method, we also describe other approaches we used, such as classic machine learning, fine-tuning open-source LLMs, and different prompting techniques. According to the official results, our team placed 6th out of 8 participants in Track 1 with a QWK of 0.729. In Track 3, we secured 4th place out of 9 with a QWK of 0.674, and we also placed 4th out of 8 in Track 4 with a QWK of 0.49.