Central College’s Stavros Papakonstantinidis, associate professor of communication studies, publishes new research on the emerging role of large language models (LLMs) in academic feedback for student writing in the highly ranked Q1 journal, “Language Testing in Asia.”
The co-authored article titled “From Red Ink to Algorithms: Investigating the Use of Large Language Models in Academic Writing Feedback” examines feedback provided by two human graders and two LLMs — ChatGPT-4.5 and Claude-3.7 Sonnet — on argumentative and reflective essays written by students from diverse linguistic backgrounds. According to the findings, human graders excel at understanding context and offering holistic guidance, while AI-generated feedback demonstrates superior structure and efficiency.
The authors’ research demonstrates how educators can enhance AI-generated feedback through tailored conversational prompting strategies, suggesting that a blended approach combining AI’s structural consistency with human expertise in higher-order analysis offers the most effective educational outcomes.
Papakonstantinidis joined Central’s communications department in 2021. He holds a Bachelor of Arts degree from State University of New York at New Paltz, earned his Master of Science from Ithaca College and obtained his Doctor of Philosophy from University of Leicester, United Kingdom.
