Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval
Not on the map. Why?
Abstract (arXiv)
Query expansion is the reformulation of a user query by adding semantically related information, and is an essential component of monolingual and cross-lingual information retrieval used to ensure that relevant documents are not missed. Recently, multilingual large language models (mLLMs) have shifted query expansion from semantic augmentation with synonyms and related words to pseudo-document generation. Pseudo-documents both introduce additional relevant terms and bridge the gap between short queries and long documents, which is particularly beneficial in dense retrieval. This study evaluates recent mLLMs and fine-tuned variants across several generative expansion strategies to identify factors that drive cross-lingual retrieval performance. Results show that query length largely determines which prompting technique is effective, and that more elaborate prompts often do not yield further gains. Substantial linguistic disparities persist: cross-lingual query expansion can produce the largest improvements for languages with the weakest baselines, yet retrieval is especially poor between languages written in different scripts. Fine-tuning is found to lead to performance gains only when the training and test data are of similar format. These outcomes underline the need for more balanced multilingual and cross-lingual training and evaluation resources.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 24 Nov 2025.
Builds on
25 of 59 references.
References · 25
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
- 2020Language-agnostic BERT Sentence Embeddingcited by 627
- 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
- 2019On the Cross-lingual Transferability of Monolingual Representationscited by 578
- 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
- 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 488
- 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 340
- 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 153
- 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
- 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
- 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
- 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
13 more
- 2023Query Expansion by Prompting Large Language Modelscited by 57
- 2023Information Retrieval: Recent Advances and Beyondcited by 49
- 2020LAReQA: Language-agnostic answer retrieval from a multilingual poolcited by 42
- 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
- 2023Generative Relevance Feedback with Large Language Modelscited by 20
- 2024Exploring the Best Practices of Query Expansion with Large Language Modelscited by 17
- 2025LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queriescited by 10
- 2025XRAG: Cross-lingual Retrieval-Augmented Generationcited by 9
- 2025Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansioncited by 6
- 2025Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Surveycited by 5
- 2025Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learningcited by 5
- 2024Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labelingcited by 3
- 2025Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignmentcited by 3
Built on by
Not cited yet.