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

Source: [XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation](<https://www.sota2.com/research/paper/69799832a2b28e761d87cc98>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-29T05:00:05.135Z

Authors: Youssef Mohamed, Mohamed Elhoseiny, Thibault Formal, Nadezhda Chirkova

Published: 2026-01-26T19:00:11.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.18886>)

[PDF](<https://arxiv.org/pdf/2601.18886.pdf>)
