SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

[2606.18801] SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2606.18801 (cs) [Submitted on 17 Jun 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval Authors: Youngjoon Jang , Seongtae Hong , Hyeonseok Moon , Heuiseok Lim View PDF HTML (experimental) Abstract: With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access. MLIR enables users to retrieve semantically relevant documents from multilingual text collections using a single-language query. However, recent multilingual dense retrieval models often exhibit a strong preference for documents in the same language as the query. This leads to severe language bias, where top-ranked results are dominated by documents of specific languages, even when documents in other languages contain more semantically relevant information. To address this issue, we propose SHIFT, a training-free method applicable in the indexing stage. Specifically, SHIFT utilizes parallel translation pairs to estimate a relative language vector for each target language with respect to a source language. Subsequently, SHIFT corrects the language-specific offset by subtracting this relative language vector from document embeddings during indexing. Our comprehensive evaluation across four MLIR benchmarks and diverse dense retrieval models confirms that SHIFT can effectively mitigate language bias and enhance MLIR performance. Comments: EMNLP 2026 Findings Subjects: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2606.18801 [cs.IR] (or arXiv:2606.18801v2 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2606.18801 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Youngjoon Jang [ view email ] [v1] Wed, 17 Jun 2026 08:14:51 UTC (1,322 KB) [v2] Thu, 27 Aug 2026 06:30:24 UTC (1,296 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 | 2026-06 Change to browse by: cs cs.AI References & Citations SciX 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)

Related documents

• SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval#677644
• ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions#1069855
• HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models#328700
• HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA#670269
• HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA#668204