Cross-Rubric Generalization for Critical Thinking Essay Scoring

Jul 16, 2026

Researchers investigate cross-rubric generalization in automated essay scoring, where models trained on essays labeled with one set of rubrics are evaluated on essays scored with previously unseen rubrics. By introducing rubric-agnostic intermediate representations called 'traits' and using a fine-tuning framework, they achieve a 5.0% macro F1 improvement over baselines in the most challenging setting. Their best open-source Llama-based model also outperforms GPT-5-mini prompting by 2.1% macro F1.

Why it matters: This work demonstrates a method for automated essay scoring systems to adapt to new or revised scoring rubrics without retraining, addressing a practical challenge in educational assessment.

Full story at: arXiv Computers and Society ↗