XProvence实现多语言零成本上下文裁剪，提升RAG效率
XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation
- 基于16种语言训练，通过跨语言迁移支持100+语言
- 在4个多语言问答基准上实现高效裁剪，性能几乎无损
- 无需额外计算，适合多语言RAG系统部署
本文提出XProvence，一种面向多语言检索增强生成（RAG）的零成本上下文裁剪模型，基于16种语言训练，并通过有效的跨语言迁移支持100+种语言。针对RAG系统在多语言场景下的日益增长需求，我们探索了将Provence框架——首次将高效零成本上下文裁剪直接集成到重排序模型中——从英语扩展至多语言的方法。在四个多语言问答基准测试中，XProvence可实现对RAG上下文的有效裁剪，且性能下降极小，显著优于多个强基线模型。模型已开源，地址为 https://huggingface.co/naver/xprovence-reranker-bgem3-v2。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。