mlsanityData to 7 Oct 2026

Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages

arXiv 2312.16159 ↗First posted 26 Dec 2023cs.IR cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have shown impressive zero-shot capabilities in various document reranking tasks. Despite their successful implementations, there is still a gap in existing literature on their effectiveness in low-resource languages. To address this gap, we investigate how LLMs function as rerankers in cross-lingual information retrieval (CLIR) systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) and we examine cross-lingual reranking with queries in English and passages in the African languages. Additionally, we analyze and compare the effectiveness of monolingual reranking using both query and document translations. We also evaluate the effectiveness of LLMs when leveraging their own generated translations. To get a grasp of the effectiveness of multiple LLMs, our study focuses on the proprietary models RankGPT-4 and RankGPT-3.5, along with the open-source model, RankZephyr. While reranking remains most effective in English, our results reveal that cross-lingual reranking may be competitive with reranking in African languages depending on the multilingual capability of the LLM.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 26 Dec 2023.

Builds on

17 of 28 references.

References · 17

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  2. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  4. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  5. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  6. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  7. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  8. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  9. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  10. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  11. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
  12. 2019Multi-Stage Document Ranking with BERTcited by 200
5 more
  1. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 151
  2. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
  3. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  4. 2022Towards Best Practices for Training Multilingual Dense Retrieval Modelscited by 26
  5. 2023Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrievalcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentationcited by 12
  2. 2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Rerankingcited by 8
  3. 2025ContextPilot: Fast Long-Context Inference via Context Reusecited by 8
  4. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answeringcited by 4
  5. 2025Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrievalcited by 1
  6. 2025Vote-in-Context: Turning VLMs into Zero-Shot Rank Fuserscited by 1
  7. 2026Non-negative Elastic Net Decoding for Information Retrievalcited by 1
  8. 2026From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Rankingcited by 0