arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.04920cs.CLcs.AI

模拟LLM对LLM的多语言数学反馈辅导

Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback

Mohamed bin Zayed University of Artificial Intelligence（莫莫德·本·泽德人工智能大学）

Junior Cedric Tonga, KV Aditya Srivatsa, Kaushal Kumar Maurya, Fajri Koto, Ekaterina Kochmar

备注：
Preprint, in submission
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文首次通过LLM模拟多语言师生互动，在11种语言和4种先进LLM上探索352种设置，发现与学生母语一致的多语言反馈能显著提升低资源语言中的数学学习效果。

摘要：

大型语言模型（LLMs）已展现出生成英语形成性反馈和教学提示的能力，这使其在AI辅助教育中日益重要。然而，它们在不同语言中提供有效教学支持的能力，尤其是针对数学推理任务，仍未得到充分研究。本文首次利用LLMs进行了大规模多语言师生互动模拟。一个更强的模型扮演导师角色，以提示形式生成反馈，而一个较弱的模型模拟学生。我们探索了352种实验设置，涵盖11种类型学上多样的语言、四种最先进的LLMs以及多种提示策略，以评估语言特定的反馈是否能带来可衡量的学习收益。我们的研究考察了学生输入语言、教师反馈语言、模型选择以及语言资源水平如何共同影响表现。结果表明，多语言提示可以显著改善学习成果，特别是在低资源语言中，当反馈与学生母语一致时效果尤为明显。这些发现为开发既有效又具包容性的多语言、基于LLM的教育工具提供了实用见解。

英文摘要：

Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them increasingly relevant for AI-assisted education. However, their ability to provide effective instructional support across different languages, especially for mathematically grounded reasoning tasks, remains largely unexamined. In this work, we present the first large-scale simulation of multilingual tutor-student interactions using LLMs. A stronger model plays the role of the tutor, generating feedback in the form of hints, while a weaker model simulates the student. We explore 352 experimental settings across 11 typologically diverse languages, four state-of-the-art LLMs, and multiple prompting strategies to assess whether language-specific feedback leads to measurable learning gains. Our study examines how student input language, teacher feedback language, model choice, and language resource level jointly influence performance. Results show that multilingual hints can significantly improve learning outcomes, particularly in low-resource languages when feedback is aligned with the student's native language. These findings offer practical insights for developing multilingual, LLM-based educational tools that are both effective and inclusive.

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。

↑