Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments
This addresses the problem of scalable and fair assessment grading for educators, especially in mathematics courses, by integrating LLMs with human oversight to reduce workload without compromising accuracy.
The paper tackles the challenge of providing timely, individualized feedback on handwritten student work at scale by presenting a scalable, end-to-end workflow for LLM-assisted grading of short, pen-and-paper assessments, reducing grading time by approximately 23% while maintaining agreement comparable to manual grading.
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.