Saved in:
Bibliographic Details
Main Authors: Perš, Janez, Muhovič, Jon, Košir, Andrej, Murovec, Boštjan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.00730
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909980017295360
author Perš, Janez
Muhovič, Jon
Košir, Andrej
Murovec, Boštjan
author_facet Perš, Janez
Muhovič, Jon
Košir, Andrej
Murovec, Boštjan
contents Handwritten STEM exams capture open-ended reasoning and diagrams, but manual grading is slow and difficult to scale. We present an end-to-end workflow for grading scanned handwritten engineering quizzes with multimodal large language models (LLMs) that preserves the standard exam process (A4 paper, unconstrained student handwriting). The lecturer provides only a handwritten reference solution (100%) and a short set of grading rules; the reference is converted into a text-only summary that conditions grading without exposing the reference scan. Reliability is achieved through a multi-stage design with a format/presence check to prevent grading blank answers, an ensemble of independent graders, supervisor aggregation, and rigid templates with deterministic validation to produce auditable, machine-parseable reports. We evaluate the frozen pipeline in a clean-room protocol on a held-out real course quiz in Slovenian, including hand-drawn circuit schematics. With state-of-the-art backends (GPT-5.2 and Gemini-3 Pro), the full pipeline achieves $\approx$8-point mean absolute difference to lecturer grades with low bias and an estimated manual-review trigger rate of $\approx$17% at $D_{\max}=40$. Ablations show that trivial prompting and removing the reference solution substantially degrade accuracy and introduce systematic over-grading, confirming that structured prompting and reference grounding are essential.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00730
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Grading Handwritten Engineering Exams with Multimodal Large Language Models
Perš, Janez
Muhovič, Jon
Košir, Andrej
Murovec, Boštjan
Computer Vision and Pattern Recognition
Handwritten STEM exams capture open-ended reasoning and diagrams, but manual grading is slow and difficult to scale. We present an end-to-end workflow for grading scanned handwritten engineering quizzes with multimodal large language models (LLMs) that preserves the standard exam process (A4 paper, unconstrained student handwriting). The lecturer provides only a handwritten reference solution (100%) and a short set of grading rules; the reference is converted into a text-only summary that conditions grading without exposing the reference scan. Reliability is achieved through a multi-stage design with a format/presence check to prevent grading blank answers, an ensemble of independent graders, supervisor aggregation, and rigid templates with deterministic validation to produce auditable, machine-parseable reports. We evaluate the frozen pipeline in a clean-room protocol on a held-out real course quiz in Slovenian, including hand-drawn circuit schematics. With state-of-the-art backends (GPT-5.2 and Gemini-3 Pro), the full pipeline achieves $\approx$8-point mean absolute difference to lecturer grades with low bias and an estimated manual-review trigger rate of $\approx$17% at $D_{\max}=40$. Ablations show that trivial prompting and removing the reference solution substantially degrade accuracy and introduce systematic over-grading, confirming that structured prompting and reference grounding are essential.
title Grading Handwritten Engineering Exams with Multimodal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.00730