The reviewed record of science sign in
Pith

arxiv: 2408.11728 · v1 · pith:RFEGH4Q4 · submitted 2024-08-21 · math.HO

AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams

Tianyi Liu , Julia Chatain , Laura Kobel-Keller , Gerd Kortemeyer , Thomas Willwacher , Mrinmaya Sachan This is my paper

Reviewed by Pithpith:RFEGH4Q4open to challenge →

classification math.HO
keywords gradinggpt-4handwrittenautomatedfeedbackmathematicspre-trainedresponse
0
0 comments X
read the original abstract

Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of semi-open and open-ended essays, have been facilitated by advances in machine learning. The emergence of pre-trained Large Language Models, such as GPT-4, offers promising new opportunities for efficiently processing diverse response types with minimal customization. This study evaluates the effectiveness of a pre-trained GPT-4 model in grading semi-open handwritten responses in a university-level mathematics exam. Our findings indicate that GPT-4 provides surprisingly reliable and cost-effective initial grading, subject to subsequent human verification. Future research should focus on refining grading rules and enhancing the extraction of handwritten responses to further leverage these technologies.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions

    cs.CV 2026-01 unverdicted novelty 6.0

    EDU-CIRCUIT-HW reveals large latent recognition failures in MLLMs on real handwritten university STEM solutions, limiting auto-grading reliability, though hybrid human-AI routing of only 3.3% cases improves outcomes.

  2. Testing the Validity of Embedding-Based Similarity and Clustering for Handwritten Physics Solutions

    physics.ed-ph 2026-06 unverdicted novelty 4.0

    Embedding similarity of physics solutions correlates modestly with human scores but clusters are score-enriched rather than score-equivalent due to surface-feature sensitivity.

  3. Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs

    cs.CY 2026-05 unverdicted novelty 4.0

    Vision LLMs achieve high rubric-level accuracy on handwritten math but most errors stem from transcription failures rather than rubric misapplication.