mlsanityData to 14 Oct 2026

XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation

arXiv 2601.18886 ↗First posted 26 Jan 2026cs.IR cs.CLcited by 2

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

This paper introduces XProvence, a multilingual zero-cost context pruning model for retrieval-augmented generation (RAG), trained on 16 languages and supporting 100+ languages through effective cross-lingual transfer. Motivated by the growing use of RAG systems across diverse languages, we explore several strategies to generalize the Provence framework-which first integrated efficient zero-cost context pruning directly into the re-ranking model-beyond English. Across four multilingual question answering benchmarks, we show how XProvence can prune RAG contexts with minimal-to-no performance degradation and outperforms strong baselines. Our model is available at https://huggingface.co/naver/xprovence-reranker-bgem3-v2.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 28 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

26 of 28 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Provence: efficient and robust context pruning for retrieval-augmented generation27 Jan
  2. 2025PISCO: Pretty Simple Compression for Retrieval-Augmented Generation27 Jan
  3. 2024CompAct: Compressing Retrieved Documents Actively for Question Answering12 Jul
  4. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token22 May
  5. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation6 Oct
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 20

  1. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  3. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  4. 2019Passage Re-ranking with BERTcited by 645
  5. 2019How multilingual is Multilingual BERT?cited by 645
  6. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 578
  7. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 488
  8. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  9. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  10. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  11. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  12. 2019Cross-Lingual Ability of Multilingual BERT: An Empirical Studycited by 182
8 more
  1. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 153
  2. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  3. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  4. 2024MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answeringcited by 43
  5. 2025Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Studycited by 38
  6. 2024Retrieval-augmented generation in multilingual settingscited by 27
  7. 2023xPQA: Cross-Lingual Product Question Answering across 12 Languagescited by 10
  8. 2024DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressorscited by 1
  2. 2026Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
  2. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
  3. 2025XRAG: Cross-lingual Retrieval-Augmented Generation
  4. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  5. 2024PersianRAG: A Retrieval-Augmented Generation System for Persian Language
  6. 2020Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval
  7. 2024Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation
  8. 2024Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study