RETUYT-INCO team applied meta-prompting with LLMs to German short-answer rubric scoring and placed 4th-6th across three tracks with QWK scores of 0.729, 0.674, and 0.49.
InProceed- ings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting in Rubric-based Scoring for German
RETUYT-INCO team applied meta-prompting with LLMs to German short-answer rubric scoring and placed 4th-6th across three tracks with QWK scores of 0.729, 0.674, and 0.49.