Confidence-Aware Automated Assessment of Student-Drawn Scientific Models

2026-06-18

AI Summary

This study addresses the high cost and limited scalability of manual scoring for student-drawn scientific models by proposing a confidence-aware automated scoring framework. The approach leverages a parameter-efficient Vision Transformer adapter combined with test-time uncertainty estimation to generate response-level confidence scores, enabling a hybrid mechanism that automatically scores high-confidence responses while routing low-confidence ones for human review. This work is the first to integrate response-level confidence signals into selective automation decisions in educational assessment. Evaluated across six middle school science tasks aligned with the Next Generation Science Standards (NGSS), the method significantly enhances scoring reliability and effectively balances automation coverage against scoring risk.

Abstract

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.

Problem

• automated scoring
• student-drawn scientific models
• confidence-aware assessment
• educational assessment
• large-scale implementation

Innovation

• confidence-aware scoring
• Vision Transformer
• automated assessment
• student-drawn models
• selective automation