# Hierarchical Document Refinement for Long-context Retrieval-augmented Generation Source: [Hierarchical Document Refinement for Long-context Retrieval-augmented Generation]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:40:15.707Z Authors: Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Qi Ye, Zhicheng Dou Published: 2025-05-15T15:34:15.000Z ## Abstract 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. ## 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. - [Multi-hop Question Answering on Dragonball DragSingleZh (test)](): Multi-hop Question Answering; Dragonball DragSingleZh (test); Recall: 15.79. - [Multi-hop Question Answering on Dragonball DragBalance (test)](): Multi-hop Question Answering; Dragonball DragBalance (test); Recall: 24.72. - [Multi-hop Question Answering on HotpotQA (test)](): Multi-hop Question Answering; HotpotQA (test); F1: 43.18. - [Multi-hop Question Answering on 2WikiMultiHopQA (test)](): Multi-hop Question Answering; 2WikiMultiHopQA (test); EM: 8. ## Original sources and implementation [Original paper]() [PDF]()