MIMO: Multilingual Information Retrieval via Monolingual Objectives

[2605.31171] MIMO: Multilingual Information Retrieval via Monolingual Objectives Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2605.31171 (cs) [Submitted on 29 May 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: MIMO: Multilingual Information Retrieval via Monolingual Objectives Authors: Youngjoon Jang , Seongtae Hong , Heuiseok Lim View PDF HTML (experimental) Abstract: 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. Comments: EMNLP 2026 Main Subjects: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2605.31171 [cs.IR] (or arXiv:2605.31171v2 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2605.31171 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Youngjoon Jang [ view email ] [v1] Fri, 29 May 2026 11:34:15 UTC (184 KB) [v2] Thu, 27 Aug 2026 06:26:06 UTC (184 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.IR < prev | next > new | recent | 2026-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• MIMO: Multilingual Information Retrieval via Monolingual Objectives#674419
• “Identifying Phrasal Connectives in Italian Using Quantitative Methods”#778687
• Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns#615094
• Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns#614127
• Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns#363261