FoL 2026
EDM

Confusion-Aware Rubric Optimization for LLM-based Automated Grading

Thu Jul 2, 10:45 AM–11:10 AM · North 209
Part of Automated Assessment
Automated Assessment & Scoring Generative AI & Large Language Models Prompt Engineering & RAG
★ 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

Optimizes automated grading rubrics by detecting and resolving confusion-causing ambiguities, improving the consistency of LLM-based graders.

Authors

Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Joseph Krajcik, Namsoo Shin, Jiliang Tang