Comparing Teacher and LLM Feedback as Dialogic Practice

• In Event: From Dashboards to Dialogues: Reimagining Teacher Preparation through AI, Media Literacy, and Transnational Partnerships

Abstract

Effective writing feedback is a powerful tool for enhancing student learning, yet teachers face many challenges that prevent them from consistently providing it. Recent advances in generative artificial intelligence (AI) have led researchers to experiment with AI tools to provide feedback, with mixed results. In this study, we used qualitative methods to compare LLM writing feedback and expert teacher (n = 12) feedback. Using a framework of dialogic writing feedback as our analytic lens, we highlight differences in LLM and teacher feedback along three dimensions: cognitive, social, and structural. Our findings have implications for improving the quality of LLM feedback and shifting teachers’ practice to foreground the types of writing feedback that students will need in the age of generative AI.

Authors

• Lena Phalen, Stanford University

• Mei Tan, Stanford University

• Christopher Mah, Stanford University

• Dora Demszky, Stanford University