EE-Eval is an automated evaluation framework that represents interactivity in AI-generated explorable explanations as finite state machines, compares extracted FSMs to ideal pedagogical FSMs using graph and embedding metrics, and shows stronger alignment with human judgments than baselines across 12
A meta-analysis of llm effects on students across qualification, socialisation, and subjectification, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Interactivity: Toward Automated Assessment of AI-Generated Explorable Explanations
EE-Eval is an automated evaluation framework that represents interactivity in AI-generated explorable explanations as finite state machines, compares extracted FSMs to ideal pedagogical FSMs using graph and embedding metrics, and shows stronger alignment with human judgments than baselines across 12