How well do Large Language Models Recognize Instructional Moves? Establishing Baselines for Foundation Models in Educational Discourse
By: Kirk Vanacore, Rene F. Kizilcec
Potential Business Impact:
Helps AI understand what teachers say in class.
Large language models (LLMs) are increasingly adopted in educational technologies for a variety of tasks, from generating instructional materials and assisting with assessment design to tutoring. While prior work has investigated how models can be adapted or optimized for specific tasks, far less is known about how well LLMs perform at interpreting authentic educational scenarios without significant customization. As LLM-based systems become widely adopted by learners and educators in everyday academic contexts, understanding their out-of-the-box capabilities is increasingly important for setting expectations and benchmarking. We compared six LLMs to estimate their baseline performance on a simple but important task: classifying instructional moves in authentic classroom transcripts. We evaluated typical prompting methods: zero-shot, one-shot, and few-shot prompting. We found that while zero-shot performance was moderate, providing comprehensive examples (few-shot prompting) significantly improved performance for state-of-the-art models, with the strongest configuration reaching Cohen's Kappa = 0.58 against expert-coded annotations. At the same time, improvements were neither uniform nor complete: performance varied considerably by instructional move, and higher recall frequently came at the cost of increased false positives. Overall, these findings indicate that foundation models demonstrate meaningful yet limited capacity to interpret instructional discourse, with prompt design helping to surface capability but not eliminating fundamental reliability constraints.
Similar Papers
Beyond Correctness: Evaluating and Improving LLM Feedback in Statistical Education
Other Statistics
Helps teachers give better feedback to students.
Measuring Teaching with LLMs
Computation and Language
Helps AI judge how good teachers are.
Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses
Computers and Society
Helps students get homework help anytime, anywhere.