From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
This work addresses the problem of assessing LLMs' ability to generate effective educational questions for middle school disciplines, which is an incremental step in educational AI.
The paper tackles the challenge of evaluating Large Language Models (LLMs) in generating high-quality educational questions by introducing EQGBench, a benchmark for Chinese Educational Question Generation (EQG), and finds through evaluation of 46 models that there is significant room for improvement in generating pedagogically valuable questions.
Large Language Models (LLMs) have demonstrated remarkable capabilities in mathematical problem-solving. However, the transition from providing answers to generating high-quality educational questions presents significant challenges that remain underexplored. To advance Educational Question Generation (EQG) and facilitate LLMs in generating pedagogically valuable and educationally effective questions, we introduce EQGBench, a comprehensive benchmark specifically designed for evaluating LLMs' performance in Chinese EQG. EQGBench establishes a five-dimensional evaluation framework supported by a dataset of 900 evaluation samples spanning three fundamental middle school disciplines: mathematics, physics, and chemistry. The dataset incorporates user queries with varying knowledge points, difficulty gradients, and question type specifications to simulate realistic educational scenarios. Through systematic evaluation of 46 mainstream large models, we reveal significant room for development in generating questions that reflect educational value and foster students' comprehensive abilities.