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
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.
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
-
Reinforcement Learning for LLM Post-Training: A Survey
A survey deriving a unified policy gradient framework for LLM post-training methods and providing technical comparisons of PPO, GRPO, DPO variants.