arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.07932cs.AI
收藏

计算蓝图:利用大型语言模型生成同构数学题

Computational Blueprints: Generating Isomorphic Mathematics Problems with Large Language Models

Turing Co. Ltd.(图灵公司)

Jeong-Hoon Kim, Jinwoo Nam, Geunsik Jo

AI总结:

针对个性化数学教育对相似练习题的需求,定义同构数学题生成任务,提出CBIT框架,通过元级生成和模板变异实现高正确性与一致性,错误率低于专家题17.8%且已落地应用。

摘要:

个性化数学教育发展迅速,对大量相似练习题的需求强烈。但现有数学题生成研究多聚焦于训练神经语言模型的数据增强,而非直接教育应用。为填补这一空白,我们定义了新任务——同构数学题生成(IMPG),旨在生成源题的结构一致变体。随后,我们通过逐步优化探索了基于LLM的自动IMPG框架,建立了同构题计算蓝图(CBIT)。CBIT通过元级生成和基于模板的选择性变异,在降低生成成本的同时实现了高数学正确性和结构一致性。不同优化阶段的实证结果表明,CBIT在生成准确性和大规模成本效益上表现更优,其生成题目错误率比专家编写题目低17.8%,已在商业教育平台部署,6732名学习者产生186870次交互。

英文摘要:

Personalized mathematics education is growing rapidly, creating a strong demand for large sets of similar practice problems. Yet existing studies on mathematics problem generation have focused on data augmentation for training neural language models rather than on direct educational deployment. To bridge this gap, we define a new task, Isomorphic Math Problem Generation (IMPG), designed to produce structurally consistent variants of source problems. Subsequently, we explored LLM-based frameworks for automatic IMPG through successive refinements, and established Computational Blueprints for Isomorphic Twins (CBIT). With meta-level generation and template-based selective variation, CBIT achieves high mathematical correctness and structural consistency while reducing the cost of generation. Empirical results across refinements demonstrate that CBIT is superior on generation accuracy and cost-effectiveness at scale. Most importantly, CBIT-generated problems exhibited an error rate 17.8% lower than expert-authored items, with deployment to 6,732 learners on a commercial education platform yielding 186,870 interactions.

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。

↑