FoL 2026
AIED

On Generating and Validating Erroneous Examples in CS1 using LLMs

Fri Jul 3, 11:45 AM–12:00 PM · R2 (Auditorium Meeting 2)
★ Notable speakers
Mariana Silva — Computer-based assessments; LLMs for automated grading; computing education technology at scale

Examines how LLMs can generate and validate erroneous code examples for use in introductory CS courses to support learning from mistakes.

Authors

Yuxuan Chen, Chenyan Zhao, Jacob Levine, Kangyu Feng, Max Fowler, Mariana Silva