AdaMCoT：通过自适应多语言链式思考重新思考跨语言事实推理
AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought
AI总结：
本文提出AdaMCOT框架，通过动态路由中间'思考语言'中的推理过程提升多语言事实推理能力，实验表明在低资源语言中表现显著提升。
摘要：
大型语言模型（LLMs）通过在多样化语料上预训练展示了出色的多语言能力。尽管这些模型表现出强大的推理能力，但其在不同语言间的性能差异显著，这是由于训练数据分布不平衡所致。现有方法在大规模多语言预训练和跨语言调优中面临可扩展性挑战，往往无法捕捉跨语言的细微推理过程。本文介绍AdaMCOT（自适应多语言链式思考），通过在生成目标语言响应前动态路由中间'思考语言'中的推理过程，增强多语言事实推理能力。AdaMCOT利用语言无关的核心，并结合自适应、基于奖励的机制选择最优推理路径，无需额外预训练。在多个基准上的全面评估显示，该方法在事实推理质量和跨语言一致性方面均有显著提升，特别是在低资源语言设置中表现尤为突出。对模型隐藏状态和语义空间的深入分析进一步阐明了该方法的内在机制。结果表明，自适应推理路径可以有效缩小高、低资源语言之间的性能差距，同时保持文化和语言的细微差别。
英文摘要：
Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their performance varies significantly between languages due to the imbalanced distribution of training data. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce AdaMCOT (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses. AdaMCOT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model's hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high and low-resource languages while maintaining cultural and linguistic nuances.
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。
