mlsanityData to 14 Oct 2026

Multilingual Generative Retrieval via Cross-lingual Semantic Compression

arXiv 2510.07812 ↗First posted 9 Oct 2025cs.CLcited by 4

Not on the map. Why?

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.

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

20 of 33 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  9. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  10. 2021mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Datasetcited by 116
  11. 2023Learning to Tokenize for Generative Retrievalcited by 68
  12. 2022Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generationcited by 48
8 more
  1. 2024Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendationscited by 31
  2. 2023Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategiescited by 25
  3. 2023Generative Retrieval via Term Set Generationcited by 13
  4. 2020A Study of Neural Matching Models for Cross-lingual IRcited by 12
  5. 2019Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representationscited by 11
  6. 2021Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancementcited by 8
  7. 2020Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commercecited by 5
  8. 2024Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraintscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Modelscited by 1
  2. 2026Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrievalcited by 0
  3. 2026Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encodercited by 0
  4. 2026Do Multilingual Encoders Produce Language-Consistent Semantic IDs?cited by 0