用大模型自动生成低资源语言数学题的本地化数据，打破英语中心偏见。
Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages
- 利用大模型自动替换数学题中的文化实体，实现本地化
- 本地化后模型在多语言任务上表现更稳健，减少英语偏见
- 适合做多语言数学推理与跨文化AI研究的团队使用
大型语言模型（LLMs）在解决自然语言表达的数学问题方面表现出显著能力。然而，由于缺乏反映真实本土实体（如人名、组织名、货币）的社会文化数据集，低资源语言的多语言与文化相关数学推理仍落后于英语。现有多语言基准大多通过翻译生成，通常保留英语中心的实体，因人工标注本地化成本高昂。此外，自动化本地化工具有限，导致真正本地化的数据集稀缺。为此，我们提出一种基于LLM的文化本地化框架，可从现有资源中自动构建包含本地名称、组织和货币的数学题数据集。实验表明，翻译基准可能掩盖真实多语言数学能力；而我们的方法能有效缓解英语中心实体偏见，并在多种语言中引入本土实体后提升模型鲁棒性。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags behind English due to the scarcity of socio-cultural task datasets that reflect accurate native entities such as person names, organization names, and currencies. Existing multilingual benchmarks are predominantly produced via translation and typically retain English-centric entities, owing to the high cost associated with human annotater-based localization. Moreover, automated localization tools are limited, and hence, truly localized datasets remain scarce. To bridge this gap, we introduce a framework for LLM-driven cultural localization of math word problems that automatically constructs datasets with native names, organizations, and currencies from existing sources. We find that translated benchmarks can obscure true multilingual math ability under appropriate socio-cultural contexts. Through extensive experiments, we also show that our framework can help mitigate English-centric entity bias and improves robustness when native entities are introduced across various languages.
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。