# Query-aware routing for Cross-lingual performance gains in Encoders

arXiv: https://arxiv.org/abs/2610.02875 · HTML: https://mlsanity.com/paper/2610.02875/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [jina-embeddings-v3: Multilingual Embeddings With Task LoRA](https://mlsanity.com/paper/2409.10173/) (2024)
- [Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup](https://mlsanity.com/paper/2101.06983/) (2021)
- [Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval](https://mlsanity.com/paper/2108.08787/) (2021)
- [Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters](https://mlsanity.com/paper/2212.10448/) (2022)
- [Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment](https://mlsanity.com/paper/2604.05684/) (2026)
- [CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training](https://mlsanity.com/paper/2604.05821/) (2026)
- [Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval](https://mlsanity.com/paper/2408.10536/) (2024)
- [Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search](https://mlsanity.com/paper/2601.04646/) (2026)

## Abstract (arXiv)

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.