探究偏差：一种多语言流水线用于生成、解决和评估LLM数学问题
Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs
AI总结：
本文提出多语言流水线生成、解决和评估数学问题，发现英语解决方案质量优于阿拉伯语，揭示语言偏差问题。
摘要：
大型语言模型（LLMs）越来越多地用于教育支持，但其响应质量因交互语言的不同而有所变化。本文提出了一种自动化多语言流水线，用于生成、解决和评估符合德国K-10课程标准的数学问题。我们生成了628道数学题并将其翻译成英文、德语和阿拉伯语。三家商业LLM（GPT-4o-mini、Gemini 2.5 Flash和Qwen-plus）被提示用每种语言生成分步骤的解决方案。一个由LLM评委组成的保留面板，包括Claude 3.5 Haiku，使用比较框架评估解决方案质量。结果表明存在一致的差距，英语解决方案始终评分最高，阿拉伯语经常排名较低。这些发现突显了持续的语言偏差，并强调了教育领域中需要更公平的多语言AI系统。
英文摘要：
Large Language Models (LLMs) are increasingly used for educational support, yet their response quality varies depending on the language of interaction. This paper presents an automated multilingual pipeline for generating, solving, and evaluating math problems aligned with the German K-10 curriculum. We generated 628 math exercises and translated them into English, German, and Arabic. Three commercial LLMs (GPT-4o-mini, Gemini 2.5 Flash, and Qwen-plus) were prompted to produce step-by-step solutions in each language. A held-out panel of LLM judges, including Claude 3.5 Haiku, evaluated solution quality using a comparative framework. Results show a consistent gap, with English solutions consistently rated highest, and Arabic often ranked lower. These findings highlight persistent linguistic bias and the need for more equitable multilingual AI systems in education.
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。
