全局学习，局部表达：弥合多语言推理中的差距
Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
AI总结：
本文提出M2A方法，通过多尺度对齐与语言一致性奖励提升多语言推理，并引入GeoFact-X基准，显著增强低资源语言推理保真度。
摘要：
大型语言模型（LLMs）在数学、事实问答和代码生成等领域表现出色，但它们在用不同语言处理这些任务时的推理能力仍不发达。特别是对于斯瓦希里语或泰语等低资源语言，LLMs 常常误解提示或默认用英语推理。这种对高资源语言的隐性偏见损害了事实准确性、可解释性和信任度。我们提出 M2A，一种新颖的方法，结合多尺度多语言对齐与基于机器翻译问题的语言一致性奖励，训练模型直接且准确地在目标语言中进行推理。此外，现有的多语言基准仅评估最终答案，忽略了推理是否以预期语言进行。为弥补这一差距，我们引入 GeoFact-X，一个基于地理的多语言事实推理基准，并附带五种语言的推理轨迹：英语、印地语、日语、斯瓦希里语和泰语。我们的结果表明，M2A 显著提高了数学和事实推理任务中的多语言推理保真度，突显了推理感知的多语言强化学习对于稳健的跨语言泛化至关重要。https://jd730.github.io/projects/M2A_GeoFact-X
英文摘要：
Large Language Models (LLMs) have achieved strong performance in domains like mathematics, factual question answering, and code generation, yet their ability to reason on these tasks in different languages remains underdeveloped. Especially for low-resource languages such as Swahili or Thai, LLMs can often misinterpret prompts or default to reasoning in English. This implicit bias toward high-resource languages undermines factual accuracy, interpretability, and trust. We propose M2A, a novel method that combines multi-scale multilingual alignment with language-consistency rewards on machine-translated questions, training models to reason directly and accurately in the target language. Furthermore, existing multilingual benchmarks only evaluate on final answers, overlooking whether reasoning occurs in the intended language. To close this gap, we introduce GeoFact-X, a geography-based multilingual factual reasoning benchmark together with reasoning traces in five languages: English, Hindi, Japanese, Swahili, and Thai. Our results show that M2A significantly enhances multilingual reasoning fidelity in both mathematical and factual reasoning tasks, highlighting that reasoning-aware multilingual reinforcement learning is crucial for robust cross-lingual generalization. https://jd730.github.io/projects/M2A_GeoFact-X
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。
