用分层结构精简长文档，提速降耗还提准
Hierarchical Document Refinement for Long-context Retrieval-augmented Generation
- 通过双级查询分析与分层文档结构，自动识别并压缩冗余内容
- 在7个数据集上达到顶尖效果，计算成本降低10倍、延迟更低
- 适合需要高效处理长文本的现实RAG应用，可直接接入现有系统
真实场景中的检索增强生成（RAG）常面临长文本输入问题，冗余信息和噪声导致推理成本高、性能下降。为此，我们提出 LongRefiner，一种高效即插即用的文档精炼器，利用长文档固有的结构特性。LongRefiner 采用双级查询分析、分层文档构建，并基于单一基础模型的多任务学习实现自适应精炼。在7个问答数据集上的实验表明，LongRefiner 在多种场景下表现优异，相比最佳基线，计算成本降低10倍，延迟显著减少。进一步分析验证了其可扩展性、高效性与有效性，为实际长文本RAG应用提供了实用洞见。代码已公开于 https://github.com/ignorejjj/LongRefiner。
原文摘要 · Abstract (English)
Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to the best baseline. Further analysis validates that LongRefiner is scalable, efficient, and effective, providing practical insights for real-world long-text RAG applications. Our code is available at https://github.com/ignorejjj/LongRefiner.
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。