# Confidence-Aware Automated Assessment of Student-Drawn Scientific Models

arXiv: https://arxiv.org/abs/2606.20264 · HTML: https://mlsanity.com/paper/2606.20264/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [NERIF: GPT-4V for Automatic Scoring of Drawn Models](https://mlsanity.com/paper/2311.12990/) (2023)
- [Classification Confidence Estimation with Test-Time Data-Augmentation](https://mlsanity.com/paper/2006.16705/) (2020)
- [Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts](https://mlsanity.com/paper/2511.17601/) (2025)
- [Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models](https://mlsanity.com/paper/2507.23470/) (2025)

## Abstract (arXiv)

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.