从答案到问题：用于评估 LLMs 教育问题生成的 EQGBench
From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
AI总结：
本文提出 EQGBench 基准，通过包含 900 个样本、覆盖三门中学学科及五维评估框架，系统评估了 46 个主流大模型在中文教育问题生成上的表现，揭示了其在生成具有教育价值问题方面的不足。
摘要：
大型语言模型（LLMs）在数学问题解决方面展现出卓越能力。然而，从提供答案转向生成高质量教育问题带来了重大挑战，且该领域仍待深入探索。为推进教育问题生成（EQG）并促使 LLMs 生成具有教学价值和教育成效的问题，我们提出了 EQGBench，一个专为评估 LLMs 在中文 EQG 中表现而设计的综合基准。EQGBench 建立了五维评估框架，并包含一个由 900 个评估样本组成的数据集，涵盖数学、物理和化学三门基础中学学科。该数据集整合了具有不同知识点、难度梯度和题型规格的用户查询，以模拟真实教育场景。通过对 46 个主流大模型的系统评估，我们发现在生成反映教育价值并促进学生综合能力的问题方面，仍存在巨大的发展空间。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
