Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments

TL;DR

This paper introduces a scalable human-in-the-loop workflow for grading handwritten math assessments using LLMs, reducing grading time by 23% while maintaining accuracy and fairness.

Contribution

It presents a comprehensive, end-to-end system integrating LLMs with human oversight for efficient grading of handwritten assessments at scale.

Findings

LLM-assisted grading reduces workload by 23%.

System maintains grading accuracy comparable to manual methods.

Hybrid approach effectively contains model errors.

Abstract

Providing timely and individualised feedback on handwritten student work is highly beneficial for learning but difficult to achieve at scale. This challenge has become more pressing as generative AI undermines the reliability of take-home assessments, shifting emphasis toward supervised, in-class evaluation. We present a scalable, end-to-end workflow for LLM-assisted grading of short, pen-and-paper assessments. The workflow spans (1) constructing solution keys, (2) developing detailed rubric-style grading keys used to guide the LLM, and (3) a grading procedure that combines automated scanning and anonymisation, multi-pass LLM scoring, automated consistency checks, and mandatory human verification. We deploy the system in two undergraduate mathematics courses using six low-stakes in-class tests. Empirically, LLM assistance reduces grading time by approximately 23% while achieving agreement comparable to, and in several cases tighter than, fully manual grading. Occasional model errors occur but are effectively contained by the hybrid design. Overall, our results show that carefully embedded human-in-the-loop LLM grading can substantially reduce workload while maintaining fairness and accuracy.