AIED

Short, Long, or Affective: Evaluating LLM-Generated Feedback Styles for Student Learning

Thu Jul 2, 11:10 AM–11:35 AM · R2 (Auditorium Meeting 2)

Part of Automated Essay Scoring and Feedback Optimization

Automated Feedback Generative AI & Large Language Models Affect & Engagement Detection

★ Notable speakers

Neil Heffernan ★★ — ASSISTments intelligent tutoring platform; educational data mining at scale

Adam Sales ★ — Causal inference in educational data mining; combining machine learning with randomized trial analysis; principal stratification in ITS

Evaluates how short, long, and affective styles of LLM-generated feedback differ in their effects on student learning.

Authors

Eamon Worden, Morgan Lee, Abubakir Siedahmed, Adam Sales, Jiayi Zhang, Roee Shraga, Neil Heffernan