当语言塑造思维：问答中事实知识的跨语言迁移
When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering
AI总结：
本文基于语言与思维理论提出Language-to-Thought提示方法，使模型内部思维语言与知识来源对齐，在三种语言和四个模型上证明其优于英语提示推理，逆转了英语提示的优势假设。
摘要：
多语言大语言模型（LLMs）为跨语言信息获取提供了有前景的机会，但它们对事实知识的运用仍然对输入语言高度敏感。先前的工作通过英语提示和评估来解决这一问题，并假设基于英语的推理具有普遍益处。在本工作中，我们通过语言与思维理论的视角探索从非英语到英语的事实知识迁移，从而挑战这一假设。我们提出了Language-to-Thought（L2T）提示方法，使模型的内部“思维”语言与知识来源保持一致。在三种语言和四个模型上，L2T一致地优于基于英语的推理，逆转了英语提示的预期优势。我们的代码可在 https://github.com/GeomeunByeol/Language2Thought 获取。
英文摘要：
Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English prompting and evaluation, assuming that English-based reasoning is universally beneficial. In this work, we challenge that assumption by exploring factual knowledge transfer from non-English to English through the lens of Language and Thought Theory. We introduce Language-to-Thought (L2T) prompting, which aligns the model's internal ''thinking'' language with the source of knowledge. Across three languages and four models, L2T consistently outperforms English-based reasoning, reversing the expected advantage of English prompts. Our code is available at https://github.com/GeomeunByeol/Language2Thought.
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。
