y0news
← Feed
Back to feed
🧠 AI🟢 BullishImportance 6/10

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

arXiv – CS AI|Arne Vanhoyweghen, Vincent Holst, Melika Mobini, Lukas Van de Voorde, Tibo Vanleke, Bert Verbruggen, Brecht Verbeken, Andres Algaba, Sam Verboven, Marie-Anne Guerry, Filip Van Droogenbroeck, Vincent Ginis|
🤖AI Summary

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.

Key Takeaways
  • LLM-assisted grading reduces teacher workload by approximately 23% compared to fully manual grading.
  • The system maintains grading accuracy and fairness comparable to traditional manual methods through human oversight.
  • The workflow addresses the growing need for supervised in-class assessments as AI undermines take-home testing reliability.
  • Human verification and consistency checks effectively contain occasional LLM errors in the hybrid design.
  • The system was successfully deployed across six low-stakes mathematics tests in undergraduate courses.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles