AIBullisharXiv – CS AI · Mar 166/10
🧠
Human-in-the-Loop LLM Grading for Handwritten Mathematics Assessments
Researchers developed a human-in-the-loop LLM system for grading handwritten mathematics assessments that reduces grading time by 23% while maintaining accuracy comparable to manual grading. The system combines automated scanning, multi-pass LLM scoring, consistency checks, and mandatory human verification to handle pen-and-paper tests at scale.