AIED

Can Large Language Models Learn to Grade Like Teachers? A Few-Shot Study on Open-Ended Assessment

Fri Jul 3, 10:00 AM–10:15 AM · North 210

Part of LLMs for Multilingual and Automated Student Assessment

Generative AI & Large Language Models Automated Assessment & Scoring Teachers & Professional Development

★ Notable speakers

Nicoletta Di Blas ★ — Technology-enhanced learning; collaborative virtual environments; large-scale digital storytelling in education (PoliCultura); educational design research

Tests whether LLMs can replicate teacher-style grading on open-ended assessments through few-shot prompting strategies.

Authors

Valentina Scorza, Giacomo Cassano, Nicoletta Di Blas