Confidence-Aware Automated Assessment of Student-Drawn Scientific Models
For science educators and assessment designers, this work addresses the cost and scalability of scoring student drawings by introducing a confidence-aware framework that balances automation and human oversight.
The paper studies automated scoring of student-generated scientific drawings using a Vision Transformer with confidence-aware predictions, enabling selective automation that defers uncertain cases to human review. Experiments on six NGSS-aligned items show improved scoring reliability and a practical trade-off between automated coverage and scoring risk.
Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standards (NGSS). However, scoring such drawings requires expert human judgment to interpret complex visual representations, making large-scale assessment costly to implement and sustain in classroom settings. In this work, we study automated scoring of student-generated scientific drawings using a vision-based model. We evaluate a Vision Transformer (ViT) with parameter-efficient adaptation and propose a confidence-aware scoring framework that derives response-level confidence from test-time predictive distributions. This confidence signal enables selective automation by scoring high-confidence responses automatically while deferring uncertain cases for human review. Experiments on six NGSS-aligned middle school assessment items show that the proposed approach improves scoring reliability while supporting a practical trade-off between automated coverage and scoring risk, highlighting the value of confidence-aware methods for trustworthy educational assessment.