研究表明，多语言嵌入模型中的跨语言检索受到“中心性”（embedding空间中的一种几何病态）的阻碍，而非各向异性。使用Gemini、Mistral和Qwen等模型进行的研究发现，解决中心性问题可以显著改善检索对称性。此外，对于阿姆哈拉语等代表性不足的语言，零样本多语言检索性能远低于语种内微调模型，凸显了进行特定语言适应的必要性。 AI
影响 中心性被确定为多语言AI检索中的一个关键问题，需要进行度量调整和特定语言微调以实现公平的性能，特别是对于代表性不足的语言。
排序理由 该集群包含两篇学术论文，详细介绍了多语言嵌入模型和检索系统的研究结果。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.26575v1 Announce Type: new Abstract: Multilingual embedding models are deployed under the assumption that cross-lingual retrieval is symmetric: if a query in language A retrieves its translation in language B, the reverse should also hold. In practice it does not. Usin…
arXiv:2605.24556v1 Announce Type: cross Abstract: Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer relia…
Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across many languages. We argue that this assu…