通过跨语言提示探索，提升大模型在多语言下的知识调用能力。
Cross-Lingual Exploration for Parametric Knowledge
- 设计跨语言提示策略，系统探索四类影响知识检索的维度。
- 在17种语言的测试中，知识召回率显著提升，优于仅靠增加本语言数据。
- 适合需要多语言一致性的应用，如跨国知识问答与翻译系统。
大型语言模型中的参数化知识在不同语言间访问程度不均，标准推理方法常难以激活本地化事实，导致跨语言知识迁移与一致性失败。本文研究通过跨语言提示策略挖掘隐藏的事实知识，识别出直接影响参数化知识检索的四个内在维度，并在涵盖17种类型多样语言的多语言事实基准上进行评估。结果表明，跨语言探索显著提升了知识迁移与事实召回能力，相比本语言规模扩展，实现了更优的计算效率权衡。此外，跨语言一致性也得到明显改善，超出仅由准确率提升可解释的范围。整体而言，本工作确立了多语言提示探索作为解锁潜在参数知识的有效推理阶段策略。
原文摘要 · Abstract (English)
Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring cross-lingual prompting strategies. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we observe corresponding improvements in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work establishes multilingual prompt exploration as a highly effective inference-time strategy for unlocking latent parametric knowledge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。