Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval
Chao Huang, Yufeng Chen, Changhao Guan, Guang Yang, Dongze Chen, Kaiyu Huang
cs.IR, cs.CL
Submitted: 2026-08-03
Comments: 14 pages, 4 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
- Multilingual Alignment of Contextual Word Representations
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
- Unsupervised Dense Information Retrieval with Contrastive Learning
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition