# Multilingual Generative Retrieval via Cross-lingual Semantic Compression

arXiv: https://arxiv.org/abs/2510.07812 · HTML: https://mlsanity.com/paper/2510.07812/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Learning to Tokenize for Generative Retrieval](https://mlsanity.com/paper/2304.04171/) (2023)
- [Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation](https://mlsanity.com/paper/2206.10128/) (2022)
- [Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations](https://mlsanity.com/paper/2403.03008/) (2024)
- [Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies](https://mlsanity.com/paper/2305.15115/) (2023)
- [Generative Retrieval via Term Set Generation](https://mlsanity.com/paper/2305.13859/) (2023)
- [A Study of Neural Matching Models for Cross-lingual IR](https://mlsanity.com/paper/2005.12994/) (2020)
- [Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations](https://mlsanity.com/paper/1906.03492/) (2019)
- [Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement](https://mlsanity.com/paper/2112.13510/) (2021)
- [Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce](https://mlsanity.com/paper/2005.08188/) (2020)
- [Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints](https://mlsanity.com/paper/2406.18085/) (2024)

## Built on by (most cited first, 4 of 4)

- [What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models](https://mlsanity.com/paper/2511.19324/) (2025)
- [Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval](https://mlsanity.com/paper/2604.23396/) (2026)
- [Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder](https://mlsanity.com/paper/2608.19957/) (2026)
- [Do Multilingual Encoders Produce Language-Consistent Semantic IDs?](https://mlsanity.com/paper/2610.01139/) (2026)

## Abstract (arXiv)

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.