SOURCE-LINKED INTELLIGENCE

Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. This study evaluates vision-language models (VLMs) for handwritten outcome-based assessment across five dimensions: accuracy, human agreement, repeated-run reliability, error concentration, and explanation quality. Using 1,982 criterion-level records from 485 undergraduate examination answers, we compare 20 configurations spanning Qwen2.5-VL, InternVL3, Pixtral, a Donut baseline, and a cascade ensemble. Evaluation setups include zero-shot promptin

Read original source ↗ Open in workspace

recordType

paper

region

Global