mlsanityData to 14 Oct 2026

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

arXiv 2607.18767 ↗First posted 21 Jul 2026cs.CV cs.AI cs.CLcited by 0

Not on the map. Why?

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.

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

9 of 19 references.

References · 9

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
  4. 2023Performance of the Pre-Trained Large Language Model GPT-4 on Automated Short Answer Gradingcited by 15
  5. 2024Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Educationcited by 11
  6. 2025Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAGcited by 3
  7. 2026Small, Private Language Models as Teammates for Educational Assessment Designcited by 2
  8. 2026The Environmental Cost of LLMs in AIED: Reporting and Practicescited by 2
  9. 2025Overview of AI Grading of Physics Olympiad Examscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Vision-Language and Large Language Models for Automated Student Assessment in Indonesian Classrooms
  2. 2026Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education
  3. 2026Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models
  4. 2025DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images
  5. 2025Seeing the Big Picture: Evaluating Multimodal LLMs' Ability to Interpret and Grade Handwritten Student Work
  6. 2026EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
  7. 2026Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark
  8. 2025Can Vision-Language Models Evaluate Handwritten Math?