critical-thinking
Filtering by topic critical-thinking(1)Clear all filters
- PaperarXiv — AI in Education (cs.CY)15 Jul 2026
When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring
Nischal Ashok Kumar, Payu Wittawatolarn, Sana Kang, Marisa C. Peczuh et al.
Automated essay scoring research extends to cross-rubric generalization, where models trained on essays labeled under one rubric are evaluated on essays scored with different rubrics. Using a Large Language Model fine-tuning framework with rubric-agnostic intermediate 'traits', the study achieves up to 5.0% improvement in macro F1 over baselines. Results show that trait-based structure and controlled supervision enhance generalization to unseen rubrics.
Original abstract
Automated essay scoring (AES) research has largely focused on cross-prompt generalization, where essays from unseen prompts are scored while the scoring criteria are typically held constant. In practice, however, educators may revise or even introduce new rubrics in their scoring task, to evaluate different aspects of essays. We study cross-rubric generalization: training on essays labeled under one set of rubrics and evaluating on previously unseen rubrics, which target different aspects of the essay. We use a Large Language Model (LLM) fine-tuning framework with two components: rubric-agnostic intermediate representations, called traits, and target-essay supervision under seen rubrics during training. On an AES dataset augmented with multiple rubric-defined labels of student critical thinking skills, we find that traits improve macro F1 by 5.0% over a baseline without traits in the hardest setting, where both target rubrics and target essays are unseen during training. We further find that increasing target-essay supervision improves performance, with our best fine-tuned open-source Llama-based model outperforming GPT-5-mini prompting by 2.1% macro F1 and trailing GPT-5 by 1.9%. These results show that trait-based intermediate structure and controlled supervision improve generalization to unseen rubrics.