AIED

Chat-Based Support Alone May Not Be Enough: Comparing Conversational and Embedded LLM Feedback for Mathematical Proof Learning

Wed Jul 1, 3:45 PM–4:00 PM · North 210

Part of Evaluating LLM-Based Feedback for Learning and Assessment

Automated Feedback Conversational AI & Chatbot Tutors Generative AI & Large Language Models Mathematics Education

★ Notable speakers

Ken Koedinger ★★ — Cognitive Tutor; LearnLab/PSLC; cognitive science of learning and AIED

Jionghao Lin ★ — Dialogue-based intelligent tutoring, NLP for educational feedback, AI-driven tutor training

Finds that chat-only LLM feedback may be insufficient for proof learning, and compares it against feedback embedded directly in the learning environment.

Authors

Eason Chen, Sophia Judicke, Kayla Beigh, Xinyi Tang, Isabel Wang, Nina Yuan, Zimo Xiao, Chuangji Li, Shizhuo Li, Reed Luttmer, Shreya Singh, Maria Yampolsky, Naman Parikh, Yvonne Zhao, Meiyi Chen, Scarlett Huang, Anishka Mohanty, Gregory Johnson, John Mackey, Jionghao Lin, Ken Koedinger