跨语言自一致性：面向语言模型的多语言推理
Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
AI总结：
提出无监督强化学习方法，通过强制模型对跨语言等价问题产生相同答案来增强多语言推理，在MGSM上平均提升21.7%，并展现出强泛化能力。
摘要：
尽管大语言模型（LLMs）的多语言覆盖范围在扩大，但其高级推理能力仍主要局限于少数高资源语言（如英语）。为了解决这一问题，我们提出了一种无监督强化学习（RL）方法，通过强制跨语言自一致性（即模型应对不同语言的等价问题产生相同最终答案）来增强多语言推理。现有方法受限于多语言推理数据的稀缺性，且对未见语言的泛化能力较弱。我们的方法既不需要标准答案，也不需要平行数据，在MGSM的10种语言上平均提升了高达21.7%。此外，我们的方法展现出强泛化能力，在训练期间未见的MGSM语言上平均提升18.2%，在3个分布外基准测试上提升高达6.2%。这些结果表明，基于一致性的方法有潜力在无需监督数据的情况下提升LLMs的多语言能力。
英文摘要：
Despite expanding their multilingual coverage, the advanced reasoning capabilities of LLMs remain largely confined to a few high-resource languages like English. To address this, we propose an unsupervised Reinforcement Learning (RL) approach to enhance multilingual reasoning by enforcing cross-lingual self-consistency: the principle that a model should produce the same final answer for equivalent problems in different languages. Existing methods are limited by the scarcity of multilingual reasoning data and show weak generalization to unseen languages. Our approach requires neither gold answers nor parallel data, and it achieves average gains of up to 21.7% on MGSM across 10 languages. In addition, our method demonstrates strong generalization, with an 18.2% mean improvement on MGSM languages unseen during training, and up to 6.2% gain on 3 out-of-distribution benchmarks. These results show the potential of consistency-based methods to improve the multilingual capabilities of LLMs without requiring supervised data.
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。
