FoL 2026
AIED

When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment

Tue Jun 30, 10:45 AM–11:10 AM · North 201
★ Notable speakers
Zhongzhou Chen — Mastery/adaptive online learning; MOOC A/B experimentation; physics education research
Shashank Sonkar — Pedagogical alignment of LLMs; cognitive modeling of student reasoning; AI in education at scale

A paper developing methods to identify when LLM graders can be trusted, calibrating confidence scores for automated assessment.

Authors

Robinson Ferrer, Zhongzhou Chen, Shashank Sonkar