AIED

Optimizing In-Context Demonstrations for LLM-based Automated Grading

Tue Jun 30, 11:35 AM–12:00 PM · North 201

★ Notable speakers

Joseph Krajcik ★★ — Project-based learning in K-12 science education, NGSS writing team leader, learning progressions, educative curriculum materials

Jiliang Tang ★★ — Graph neural networks; deep learning on graphs; data mining; educational data mining; knowledge tracing

Yasemin Copur-Gencturk ★ — Mathematics teacher professional development; teacher knowledge measurement; technology-enhanced teacher learning

Kevin Haudek ★ — Automated NLP/ML scoring of student constructed responses in science education; director of MSU AACR group

A paper on selecting and optimizing in-context demonstrations to improve the accuracy and consistency of LLM-based automated grading.

Authors