Explainable Few-shot Knowledge Tracing
This addresses the problem for educators who need to assess students with limited data and provide explanatory feedback, representing an incremental improvement by adapting LLMs to a specific educational task.
The paper tackles the gap between traditional knowledge tracing methods and real-world teaching by introducing Explainable Few-shot Knowledge Tracing, which uses large language models to track student knowledge from limited data and provide natural language explanations, achieving comparable or superior performance to deep learning methods on three datasets.
Knowledge tracing (KT), aiming to mine students' mastery of knowledge by their exercise records and predict their performance on future test questions, is a critical task in educational assessment. While researchers achieved tremendous success with the rapid development of deep learning techniques, current knowledge tracing tasks fall into the cracks from real-world teaching scenarios. Relying heavily on extensive student data and solely predicting numerical performances differs from the settings where teachers assess students' knowledge state from limited practices and provide explanatory feedback. To fill this gap, we explore a new task formulation: Explainable Few-shot Knowledge Tracing. By leveraging the powerful reasoning and generation abilities of large language models (LLMs), we then propose a cognition-guided framework that can track the student knowledge from a few student records while providing natural language explanations. Experimental results from three widely used datasets show that LLMs can perform comparable or superior to competitive deep knowledge tracing methods. We also discuss potential directions and call for future improvements in relevant topics.