Large language models are increasingly used to simulate students at different mastery levels, providing synthetic training data and a way to stress-test tutoring systems. A new arXiv paper proposes Stochastic Student Knowledge Graphs (SSKG) as a method for faithful LLM student simulation.
According to the abstract, existing approaches primarily leverage an LLM to answer, while SSKG is introduced to improve fidelity. The paper's title, 'From Mastery Profile to Simulated Response,' suggests that the method connects a student's mastery profile to a simulated response through stochastic knowledge graphs.
The available abstract is truncated, so the full details of SSKG are not described in the source. The paper is available on arXiv under identifier 2608.21668v2.