对齐基准：双语自反馈的多语言数学推理
Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning
AI总结：
PASMR通过基准语言自反馈机制提升多语言数学推理能力，解决LLMs在多语言环境下的性能下降问题。
摘要：
尽管大型语言模型（LLMs）展现出了令人印象深刻的推理能力，但实证证据表明它们并非如预期般语言无关，导致在多语言环境下性能下降，尤其是对低资源语言而言。我们将这种下降归因于模型多语言理解和推理对齐的一致性问题。为此，我们提出了Pivot-Aligned Self-Feedback Multilingual Reasoning（PASMR），旨在提高LLMs中多语言数学推理能力的对齐。该方法将模型的主要语言指定为基准语言。在训练过程中，模型首先将问题翻译成基准语言，以促进更好的推理模式对齐。然后，目标语言的推理过程由基准语言的推理答案进行监督，从而建立一个无需外部正确答案或奖励模型的跨语言自反馈机制。广泛的实验结果表明，我们的方法增强了模型对问题的理解和推理能力，导致了显著的任务改进。
英文摘要：
Despite the impressive reasoning abilities demonstrated by large language models (LLMs), empirical evidence indicates that they are not language agnostic as expected, leading to performance declines in multilingual settings, especially for low-resource languages. We attribute the decline to the model's inconsistent multilingual understanding and reasoning alignment. To address this, we present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR), aiming to improve the alignment of multilingual math reasoning abilities in LLMs. This approach designates the model's primary language as the pivot language. During training, the model first translates questions into the pivot language to facilitate better alignment of reasoning patterns. The reasoning process in the target language is then supervised by the pivot language's reasoning answers, thereby establishing a cross-lingual self-feedback mechanism without relying on external correct answers or reward models. Extensive experimental results demonstrate that our method enhances both the model's understanding of questions and its reasoning capabilities, leading to notable task improvements.
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。
