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

• URL: http://arxiv.org/abs/2606.18801v1
• Date: Wed, 17 Jun 2026 08:14:51 GMT
• Title: SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
• Abstract summary: Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access.<n>Recent multilingual dense retrieval models often exhibit a strong preference for documents in the same language as the query.<n>We propose SHIFT, a training-free method applicable in the indexing stage.
• Score: 26.186599286240362
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• LAMAR: An Open Language-Aware Multilingual Alignment Reranker [24.064060212702838]
  We show that multilingual rerankers do not consistently prioritize documents written in the same language as the query.<n>We release LAMAR, a language aware multilingual cross encoder trained to account for both semantic relevance and language coherence.
  arXiv  Detail & Related papers  (2026-07-24T07:11:42Z)
• MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal [26.186599286240362]
  MLAIRE is a Multilingual Language-Aware Information Retrieval Evaluation protocol.<n>It disentangles cross-lingual semantic retrieval from query-language preference.<n>We show that standard metrics obscure distinct behaviors.
  arXiv  Detail & Related papers  (2026-05-08T05:10:05Z)
• Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval [0.19116784879310025]
  Multilingual large language models (mLLMs) have shifted query expansion from semantic augmentation with synonyms and related words to pseudo-document generation.<n>This study evaluates recent mLLMs and fine-tuned variants across several generative expansion strategies to identify factors that drive cross-lingual retrieval performance.
  arXiv  Detail & Related papers  (2025-11-24T17:18:25Z)
• VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding [49.07705729597171]
  VisR-Bench is a benchmark for question-driven multimodal retrieval in long documents.<n>Our benchmark comprises over 35K high-quality QA pairs across 1.2K documents.<n>We evaluate various retrieval models, including text-based methods, multimodal encoders, and MLLMs.
  arXiv  Detail & Related papers  (2025-08-10T21:44:43Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Machine-Created Universal Language for Cross-lingual Transfer [73.44138687502294]
  We propose a new Machine-created Universal Language (MUL) as an alternative intermediate language. MUL comprises a set of discrete symbols forming a universal vocabulary and a natural language to MUL translator. MUL unifies shared concepts from various languages into a single universal word, enhancing cross-language transfer.
  arXiv  Detail & Related papers  (2023-05-22T14:41:09Z)
• Soft Prompt Decoding for Multilingual Dense Retrieval [30.766917713997355]
  We show that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance. This is due to the heterogeneous and imbalanced nature of multilingual collections. We present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly "translates" the representation of documents in different languages into the same embedding space.
  arXiv  Detail & Related papers  (2023-05-15T21:17:17Z)
• Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval [80.43859162884353]
  We propose a multilingual multilingual language model called masked sentence model (MSM)<n>MSM consists of a sentence encoder to generate the sentence representations, and a document encoder applied to a sequence of sentence vectors from a document.<n>To train the model, we propose a masked sentence prediction task, which masks and predicts the sentence vector via a hierarchical contrastive loss with sampled negatives.
  arXiv  Detail & Related papers  (2023-02-03T09:54:27Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)
• A Simple and Efficient Probabilistic Language model for Code-Mixed Text [0.0]
  We present a simple probabilistic approach for building efficient word embedding for code-mixed text. We examine its efficacy for the classification task using bidirectional LSTMs and SVMs.
  arXiv  Detail & Related papers  (2021-06-29T05:37:57Z)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.