MILCO: Learned Sparse Retrieval Across Languages via a Multilingual Connector

ICLR 2026 Conference Submission22150 Authors

Keywords: learned sparse retrieval, multilingual retrieval, cross-lingual retrieval, neural lexical search

TL;DR: MILCO aligns queries and documents into a shared English lexical space with two-stage training and a LexEcho head, preserving key source tokens while ensuring strong sparse multilingual performance and efficiency via pruning.

Abstract: Learned Sparse Retrieval (LSR) combines the efficiency of bi-encoders with the transparency of lexical matching, but existing approaches struggle to scale beyond English. We introduce MILCO, an LSR architecture that maps queries and documents from different languages into a shared English lexical space via a multilingual connector. MILCO is trained with a specialized two-stage regime that combines Sparse Alignment Pretraining with contrastive training to provide representation transparency and effectiveness while mitigating semantic collapse. Motivated by the observation that uncommon entities are often lost when projected into English, we propose a new LexEcho head, which enhances robustness by augmenting the English lexical representation with a source-language view obtained through a special [ECHO] token. MILCO achieves state-of-the-art multilingual and cross-lingual LSR performance, outperforming leading dense, sparse, and multi-vector baselines such as BGE-M3 and Qwen3-Embed on standard multilingual benchmarks, while supporting dynamic efficiency through post-hoc pruning. Notably, when using mass-based pruning to reduce document representations to only 30 active dimensions on average, MILCO 560M outperforms the similarly-sized Qwen3-Embed 0.6B with 1024 dimensions.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 22150