Multilingual Generative Retrieval via Cross-lingual Semantic Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Yuxin, Wu, Simeng, Song, Ran, Xiang, Yan, Xian, Yantuan, Gao, Shengxiang, Yu, Zhengtao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914082405220352
author Huang, Yuxin
Wu, Simeng
Song, Ran
Xiang, Yan
Xian, Yantuan
Gao, Shengxiang
Yu, Zhengtao
author_facet Huang, Yuxin
Wu, Simeng
Song, Ran
Xiang, Yan
Xian, Yantuan
Gao, Shengxiang
Yu, Zhengtao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multilingual Generative Retrieval via Cross-lingual Semantic Compression
Huang, Yuxin
Wu, Simeng
Song, Ran
Xiang, Yan
Xian, Yantuan
Gao, Shengxiang
Yu, Zhengtao
Computation and Language
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.
title Multilingual Generative Retrieval via Cross-lingual Semantic Compression
topic Computation and Language
url https://arxiv.org/abs/2510.07812