# Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks

arXiv: https://arxiv.org/abs/2607.18767 · HTML: https://mlsanity.com/paper/2607.18767/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 21 Jul 2026.

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

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse](https://mlsanity.com/paper/2410.21333/) (2024)
- [Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer Grading](https://mlsanity.com/paper/2309.09338/) (2023)
- [Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education](https://mlsanity.com/paper/2405.02985/) (2024)
- [Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG](https://mlsanity.com/paper/2506.05925/) (2025)
- [Small, Private Language Models as Teammates for Educational Assessment Design](https://mlsanity.com/paper/2605.15015/) (2026)
- [The Environmental Cost of LLMs in AIED: Reporting and Practices](https://mlsanity.com/paper/2606.11215/) (2026)
- [Overview of AI Grading of Physics Olympiad Exams](https://mlsanity.com/paper/2505.02121/) (2025)

## Abstract (arXiv)

The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability. However, SLMs often struggle with complex vision-based tasks, such as grading handwritten student exams, due to the high computational cost of processing large images and the visual distractions present on a full page. In this paper, we investigate whether cropping student responses using bounding boxes can improve the accuracy and computational efficiency of SLMs on a short-answer grading task. Using a dataset of scanned handwritten responses from the 2025 Australian Physics Olympiad, we evaluate the performance of several models ranging from 4B to 72B parameters under varying conditions of Chain of Thought (CoT) prompting and image cropping. Our results demonstrate that using bounding boxes significantly improves grading accuracy and reduces computational cost (FLOPs) across models. We conclude that bounding boxes are a crucial pre-processing step for deploying SLMs in large-scale, vision-based educational assessments.