2025/05/15 by Jiajie Jin, Xiaoxi Li, Jin, Jiajie +15 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Recommender Systems and Techniques #Semantic Web and Ontologies #Web Data Mining and Analysis
paper · pdf · doi:10.48550/arxiv.2505.10413
openalex publication_date 2025/05/15 · openalex created_date 2025/10/15 · openalex updated_date 2026/07/28
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.