让大模型生成更多样化的编程练习题，避免千篇一律。
Enhancing Diversity of LLM-Generated Educational Tasks
- 分两阶段提示：先发散思考再满足题目要求
- 生成任务多样性提升约1.6倍，质量仍高
- 适合教育内容生成与智能出题场景
大型语言模型在规模化生成教育内容方面展现出潜力，可协助教师创建练习题或为教育模型训练合成数据。然而，这些模型存在“人工蜂群效应”，导致生成内容同质化，限制了任务多样性这一关键因素。本文研究如何在保持任务实用性的同时提升生成内容的多样性。受创造力文献中发散-收敛思维阶段启发，我们提出一种双阶段提示框架：(1) 探索创造性空间，(2) 满足输入需求。我们在 Python 编程领域评估了基于该框架实现的方法 CreativeDC，使用自动指标与专家评估。结果表明，CreativeDC 生成的任务在多样性上显著优于基线方法，多样性提升约 1.6 倍，且任务质量仍保持较高水平。本工作为大规模生成和评估更多样化教育任务提供了有效方案。
原文摘要 · Abstract (English)
Large language models (LLMs) have shown the potential for generating educational content at scale, assisting educators in creating practice tasks or synthesizing data for training educational models. However, LLMs suffer from the ``Artificial Hivemind'' effect, where they produce homogeneous content. This homogeneity limits the diversity of LLM-generated tasks, a crucial factor in these educational settings. In this paper, we investigate how to increase the diversity of generated tasks while keeping their utility high. Inspired by the divergent--convergent thinking stages in creativity literature, we propose a prompting framework with two reasoning stages: (1) exploring the creative space, and (2) satisfying the input requirements. We evaluate CreativeDC, a method instantiated from this framework in the domain of Python programming, using both automated metrics and expert evaluation. Results show that CreativeDC produces significantly more distinct high-utility tasks (about $1.6\times$) than baselines. Our work offers an effective approach for generating and evaluating more diverse tasks at scale.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。