arXiv：cs.AI· Akshay Jain, Edward Kim·· 4 小时前AI 评分35
面向查询感知路由的编码器跨语言检索性能提升
Query-aware routing for Cross-lingual performance gains in Encoders
AI 导读
研究者提出 SampoTron，一种基于查询的低秩（LoRA）适配器，配合 Nemotron-3-Embed-1B 模型与基于查询和索引语言的确定性路由，在英语、芬兰语、瑞典语六个跨语言检索方向上，将 nDCG@10 从 0.241 提升至 0.291，相对增益 20.9%。跨语言查询走适配器，同语言查询走原编码器，从而在保留原有同语言性能和文档索引的前提下实现选择性跨语言专精。
正文
Abstract:Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language performance. We investigate whether Finnish and Swedish cross-lingual retrieval can improve while preserving an encoder's existing same-language performance and document index. We combine a query-only low-rank adapter, trained against frozen document embeddings, with deterministic routing based on query and index languages. Cross-language queries use the adapter, while same-language queries use the original encoder. SampoTron, our fine-tuned low-rank (LoRA) adapter alongwith the Nemotron-3-Embed-1B model, improves average retrieval quality across six English, Finnish, and Swedish directions from 0.241 to 0.291 in normalized discounted cumulative gain (nDCG) at rank ten, a 20.9% relative gain on a sampled financial benchmark. All six cross-lingual directions improve, and routing preserves the original same-language performance, including two full-corpus Finnish evaluations. The approach enables selective cross-language specialization with reusable document embedding vectors.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.02875 [cs.CL] |
| (or arXiv:2610.02875v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02875 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Akshay Jain [view email]
[v1]
Fri, 2 Oct 2026 06:12:53 UTC (37 KB)
来源：arXiv：cs.AI · arxiv.org