AIED

A Comparative Study of Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics

Mon Jun 29, 3:45 PM–4:10 PM · R2 (Auditorium Meeting 2)

Part of Regulating Learning through Human and AI Feedback

Automated Feedback Generative AI & Large Language Models Writing & Language Learning Programming & CS Education

Compares technical writing feedback from large language models, small language models, and humans on computer science topics to assess relative quality.

Authors

Suqing Liu, Runlong Ye, Christopher Eaton, Bogdan Simion, Michael Liut