Multilingual Generative Retrieval via Cross-lingual Semantic Compression
Yuxin Huang, Simeng Wu, Ran Song, Yan Xiang, Yantuan Xian, Shengxiang Gao, Zhengtao Yu
Abstract
Generative Information Retrieval is an emerging retrieval paradigm that exhibits remarkable performance in monolingual scenarios. However, applying these methods to multilingual retrieval still encounters two primary challenges, cross-lingual identifier misalignment and identifier inflation. To address these limitations, we propose Multilingual Generative Retrieval via Cross-lingual Semantic Compression (MGR-CSC), a novel framework that unifies semantically equivalent multilingual keywords into shared atoms to align semantics and compresses the identifier space, and we propose a dynamic multi-step constrained decoding strategy during retrieval. MGR-CSC improves cross-lingual alignment by assigning consistent identifiers and enhances decoding efficiency by reducing redundancy. Experiments demonstrate that MGR-CSC achieves outstanding retrieval accuracy, improving by 6.83% on mMarco100k and 4.77% on mNQ320k, while reducing document identifiers length by 74.51% and 78.2%, respectively. We publicly release our dataset and code at https://github.com/simengggg/MGR-CSC
BibTeX
@inproceedings{emnlp2025_multilingualgene,
title = {Multilingual Generative Retrieval via Cross-lingual Semantic Compression},
author = {Yuxin Huang and Simeng Wu and Ran Song and Yan Xiang and Yantuan Xian and Shengxiang Gao and Zhengtao Yu},
booktitle = {EMNLP 2025},
year = {2025}
}