TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring
This work addresses a gap in automated essay scoring for educators and researchers by providing a more detailed, trait-specific evaluation method, though it is incremental as it builds on existing AES approaches.
The paper tackles the problem of automated essay scoring for individual traits rather than holistic assessment, proposing TRATES, a framework that uses LLM-generated trait-specific features combined with generic features to predict trait scores, achieving new state-of-the-art performance across all traits on a widely-used dataset.
Research on holistic Automated Essay Scoring (AES) is long-dated; yet, there is a notable lack of attention for assessing essays according to individual traits. In this work, we propose TRATES, a novel trait-specific and rubric-based cross-prompt AES framework that is generic yet specific to the underlying trait. The framework leverages a Large Language Model (LLM) that utilizes the trait grading rubrics to generate trait-specific features (represented by assessment questions), then assesses those features given an essay. The trait-specific features are eventually combined with generic writing-quality and prompt-specific features to train a simple classical regression model that predicts trait scores of essays from an unseen prompt. Experiments show that TRATES achieves a new state-of-the-art performance across all traits on a widely-used dataset, with the generated LLM-based features being the most significant.