LUSIFER: Language Universal Space Integration For Enhanced Multilingual Embeddings With Large Language Models

Abstract

Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision. LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks. These components are seamlessly integrated through a minimal set of trainable parameters that act as a connector, effectively transferring the multilingual encoder's language understanding capabilities to the specialized embedding model. Additionally, to comprehensively evaluate multilingual embedding performance, we introduce a new

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyman2025lusifer

Related papers

• Transforming Llms Into Cross-modal And Cross-lingual Retrieval Systems (2024)4.52
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• LEMUR: A Corpus For Robust Fine-tuning Of Multilingual Law Embedding Models For Retrieval (2026)0.00
• Lightretriever: A Llm-based Text Retrieval Architecture With Extremely Faster Query Inference (2025)0.00
• Breaking The Modality Barrier: Universal Embedding Learning With Multimodal Llms (2025)4.52
• Massively Multilingual Sentence Embeddings For Zero-shot Cross-lingual Transfer And Beyond (2018)26.33
• Mm-embed: Universal Multimodal Retrieval With Multimodal Llms (2024)0.00
• Magic-mm-embedding: Towards Visual-token-efficient Universal Multimodal Embedding With Mllms (2026)0.00