# MIMO: Multilingual Information Retrieval via Monolingual Objectives

arXiv: https://arxiv.org/abs/2605.31171 · HTML: https://mlsanity.com/paper/2605.31171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 22 of 22)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [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)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks](https://mlsanity.com/paper/2511.07025/) (2025)
- [LAReQA: Language-agnostic answer retrieval from a multilingual pool](https://mlsanity.com/paper/2004.05484/) (2020)
- [Training Sparse Mixture Of Experts Text Embedding Models](https://mlsanity.com/paper/2502.07972/) (2025)
- [Investigating Language Preference of Multilingual RAG Systems](https://mlsanity.com/paper/2502.11175/) (2025)
- [Overview of the TREC 2023 NeuCLIR Track](https://mlsanity.com/paper/2404.08071/) (2024)
- [EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval](https://mlsanity.com/paper/2301.12005/) (2023)
- [Overview of the TREC 2022 NeuCLIR Track](https://mlsanity.com/paper/2304.12367/) (2023)
- [NeuCLIRBench: A Modern Evaluation Collection for Monolingual, Cross-Language, and Multilingual Information Retrieval](https://mlsanity.com/paper/2511.14758/) (2025)

## Abstract (arXiv)

Multilingual Information Retrieval (MLIR) reflects real-world search environments in which queries and relevant documents may appear in different languages within a mixed-language corpus. However, existing embedding models are primarily optimized for Multi-Monolingual retrieval and their performance often degrades in MLIR settings. Moreover, directly applying conventional contrastive learning to MLIR can exacerbate language clustering and expose a trade-off between cross-lingual alignment and embedding uniformity. To address these limitations, we propose MIMO: Multilingual Information Retrieval via Monolingual Objectives, a two-stage framework that uses a stable English semantic space from a high-performing teacher model as an anchor. MIMO first initializes the student model's cross-lingual alignment through knowledge distillation, and then jointly optimizes distillation and cross-lingual contrastive learning to improve retrieval discrimination while preserving alignment. Extensive experiments show that MIMO consistently outperforms existing cross-lingual training baselines across various MLIR and Multi-Monolingual benchmarks. MIMO also remains competitive with off-the-shelf models of similar or larger parameter scales. Furthermore, our cross-lingual Alignment-Uniformity analysis clarifies the distinct roles of the two loss components and shows that their combination yields a favorable trade-off between alignment and uniformity.